- Making Model Training a Bit More Scientific (VIII): Learning Rates for Multi-Stage Training
2026-08-31Mathematics18 eqinequality learning rate optimizer SGD model tuning
- A New Understanding of Momentum: Approximating Gradient Descent at the Feature Level
2026-08-23Machine Learning11 eqlinear gradient optimizer muon
- Steepest Descent on Manifolds: 7. An Analytic Solution for Stiefel
2026-08-17Mathematics29 eqoptimizer muon constraint steepest descent
- What Alternatives to Cross-Entropy Exist for LM Loss?
2026-08-09Machine Learning17 eqoptimal language model loss function gradient
- A Brief Discussion of MoE and Attention in K3
2026-08-04Machine Learning5 eqlinear attention positional encoding MoE
- Deconstructing Scaling Laws: A Triad of Optimization, Architecture, and Data
2026-07-29Machine Learning38 eqinequality model optimization scaling law
- Turning Softmax Attention into Gated DeltaNet
2026-07-21Mathematics19 eqapproximation analysis linear attention
- A Similarity Metric Based on the Rearrangement Inequality
2026-07-16Mathematics14 eqinequality semantic similarity
- The Taylor Expansion of LogSumExp and Softmax
2026-07-13Mathematics13 eqcalculus approximation linear attention
- Making Model Training a Bit More Scientific (Part 7): Step Size Scheduling and Weight Averaging
2026-07-06Mathematics18 eqinequality learning rate optimizer SGD model tuning
- The Aesthetics of Brute Force in Approximating Matrix Functions
2026-06-25Mathematics10 eqfunction iteration approximation matrix SVD
- Margin-Enforcing Projection
2026-06-19Mathematics8 eqoptimal analysis optimization loss function
- A Tour of MoE: 9. The Debate on Gate Normalization
2026-06-17Machine Learning12 eqprobability loss function gradient MoE
- The Steepest Descent on a Manifold: 6. Muon + Double Rotation
2026-06-08Mathematics8 eqoptimizer muon constraint steepest descent
- Why does the official Muon have an extra max(1, ⋅) compared to the MuP version?
2026-06-03Machine Learning7 eqlearning rate optimizer muon MuP
- Is a higher singular-value entropy of matrix parameters always better?
2026-05-29Mathematics15 eqmatrix entropy SVD mean field
- MoE Tour: 8. Forced Sequence-Level Balancing
2026-05-22Machine Learning8 eqstatistics loss function RNN MoE
- How was DeepSeek V4's tid2eid derived?
2026-05-15Machine Learning2 eqmodel function analysis MoE
- Training Directly with FID as a Loss: From Gradient Computation to Streaming Training
2026-05-08Machine Learning14 eqmatrix loss function generative model gradient
- How to More Scientifically Estimate the Spectral Norm of a Matrix
2026-05-04Machine Learning16 eqiteration matrix estimation spectral norm
- Beyond MuP: 4. Holding the Line on Parameter Stability
2026-04-24Machine Learning21 eqmatrix stability optimizer muon MuP
- Streaming Power Iteration for Muon: 5. Extensions
2026-04-17Machine Learning9 eqiteration matrix optimizer spectral norm muon
- Streaming Power Iteration-based Muon Implementation: 4. Principles
2026-04-13Machine Learning11 eqiteration matrix SVD optimizer muon
- Muon Implementation Based on Streaming Power Iteration: 3. Refinement
2026-04-07Machine Learning6 eqiteration matrix SVD optimizer muon
- Introduction to the Median
2026-03-31Mathematics10 eqalgebra statistics probability geometry
- Muon Implementation Based on Streaming Power Iteration: 2. Acceleration
2026-03-26Machine Learning7 eqiteration matrix SVD optimizer muon
- Attention Residuals Memoir
2026-03-19Machine Learning15 eqmodel optimization attention scaling law depth
- Implementing Muon via Streaming Power Iteration: 1. First Encounter
2026-03-12Machine Learning11 eqiteration matrix SVD optimizer muon
- Above MuP: 3. Special Cases Deserve Special Treatment
2026-03-02Machine Learning18 eqinequality matrix linear optimizer MuP
- A Tour of MoE: 7. A Minimalist Explanation of Dynamic Activation
2026-02-23Machine Learning16 eqlinear duality optimization MoE dynamics
- MoE Journey: 6. Optimal Assignment Promotes Balance
2026-02-22Machine Learning21 eqlinear duality optimization gradient MoE
- Above MuP: 2. Linear Layers and Steepest Descent
2026-02-15Machine Learning15 eqmatrix linear optimizer muon MuP
- Is β1=β2 the Optimal Hyperparameter for the Adam Optimizer?
2026-02-04Machine Learning10 eqoptimal gradient optimizer steepest descent
- Translating an arXiv Paper into Chinese with One Line of Code
2026-01-28Machine Learningtranslation latex paper kimi
- The elements of DeltaNet's core inverse matrix always lie within [-1, 1]
2026-01-26Mathematics15 eqmatrix linear RNN attention
- Why Do We Favor Isotropy? An Understanding Based on Steepest Descent
2026-01-20Machine Learning10 eqgeometry gradient SGD muon
- Making Model Training a Bit More Scientific (VI): An Elegant Top-Down Construction
2026-01-16Mathematics21 eqoptimization learning rate optimizer SGD model tuning
- Making Alchemy More Scientific (V): Fine-Tuning the Learning Rate Based on Gradients
2026-01-09Mathematics28 eqgradient learning rate optimizer SGD model tuning
- Making Model Training More Scientific (IV): A New Identity, A New Learning Rate
2025-12-26Mathematics15 eqlearning rate optimizer SGD model tuning
- Why Does DeltaNet Add L2 Normalize?
2025-12-23Mathematics9 eqdifferential equation linear RNN attention
- Making Model Training More Scientific (Part 3): Convergence of the Final-Point Loss in SGD
2025-12-16Mathematics16 eqinequality optimizer SGD model tuning
- Making Alchemy a Bit More Scientific (Part 2): Extending the Conclusion to Unbounded Domains
2025-12-12Mathematics14 eqinequality optimizer SGD model tuning
- Weight Decay and Learning Rate from the Perspective of Exponential Moving Averages
2025-12-05Mathematics16 eqoptimal gradient learning rate mean field
- Diffusion Models from Scratch (31): Predict the Data, Not the Noise
2025-11-24Machine Learning1 eqloss function generative model diffusion manifold
- Muon Optimizer Guide: Getting Started Quickly and Key Details
2025-11-19Machine Learning2 eqmatrix optimization optimizer muon
- Asymptotic Estimation of AdamW's Weight RMS (Part 2)
2025-11-17Mathematics35 eqdifferential equation estimation gradient optimizer mean field
- Asymptotic Estimate of the Maximum of n Normal Random Numbers
2025-11-06Mathematics21 eqprobability approximation random estimation
- Steepest Descent on Manifolds: 5. Dual Gradient Descent
2025-11-03Mathematics12 eqmatrix optimizer muon constraint steepest descent
- Low-Precision Attention May Have Biased Rounding Errors
2025-10-27Machine Learning3 eqapproximation analysis optimization attention
- Beyond MuP: 1. Three Characteristics of a Good Model
2025-10-21Machine Learning4 eqoptimization optimizer scaling law MuP
- Fast Estimation of the Spectral Norm of Random Matrices
2025-10-12Mathematics9 eqapproximation matrix estimation spectral norm
- DiVeQ: A Remarkably Concise Training Scheme for VQ
2025-10-08Machine Learning11 eqgenerative model encoding gradient discretization
- Why Do Linear Attention Models Need Short Conv?
2025-10-05Machine Learning1 eqlinear RNN generative model attention
- AdamW's Weight RMS Asymptotic Estimate (Part 1)
2025-10-01Mathematics29 eqestimation gradient optimizer mean field
- Rethinking Learning Rate and Batch Size (IV): EMA
2025-09-22Mathematics22 eqlearning rate optimizer scaling law mean field
- Rethinking Learning Rate and Batch Size (III): Muon
2025-09-15Mathematics8 eqlearning rate optimizer scaling law muon mean field
- Rethinking Learning Rate and Batch Size (Part 2): Mean-Field Approximation
2025-09-10Mathematics23 eqlearning rate optimizer scaling law mean field
- Why Is Adam's Update RMS 0.2?
2025-09-02Mathematics13 eqanalysis gradient optimizer mean field
- Rethinking Learning Rate and Batch Size (I): The Current State of Affairs
2025-09-01Mathematics9 eqgradient learning rate optimizer scaling law
- Cool Papers Update: Simple Adaptation for Zotero Connector
2025-08-25Machine Learningwebsite paper cool paper
- Steepest Descent on Manifolds: 4. Muon + Spectral Sphere
2025-08-21Mathematics13 eqmatrix optimizer muon constraint steepest descent
- An Identity for ReLU/GeLU/Swish
2025-08-16Mathematics3 eqanalysis neural network identity
- Steepest Descent on Manifolds: 3. Muon + Stiefel
2025-08-08Mathematics17 eqmatrix optimizer muon constraint steepest descent
- The Steepest Descent on Manifolds: 2. Muon + Orthogonality
2025-08-06Mathematics19 eqmatrix optimizer muon constraint steepest descent
- Building a Portable Bypass Router with the Raspberry Pi Zero 2 W
2025-08-02Machine Learninglinux network router smart home
- Steepest Descent on Manifolds: 1. SGD + Hypersphere
2025-08-01Mathematics16 eqinequality optimizer constraint steepest descent
- Efficient Computation of Matrix r-th Roots and Inverse r-th Roots
2025-07-21Mathematics14 eqalgebra iteration matrix linear
- Efficient Computation of Matrix Square Roots and Inverse Square Roots
2025-07-19Mathematics14 eqalgebra iteration matrix linear
- QK-Clip: Pushing Muon Further Along the Path of Scale-Up
2025-07-12Machine Learning14 eqoptimization attention optimizer muon
- The Road to Transformer Upgrades: 21. What Makes MLA Good? (Part 2)
2025-07-10Machine Learning3 eqoptimization language model generative model attention
- Efficient Inversion of "Diagonal + Low-Rank" Triangular Matrices
2025-07-01Mathematics9 eqcomputation matrix RNN attention
- Computing Singular Value Clipping mclip via msign (Part 2)
2025-06-23Mathematics16 eqiteration approximation matrix SVD muon
- What Can the Matrix Sign Function mcsgn Compute?
2025-06-23Mathematics12 eqalgebra matrix linear
- A Brief History of Linear Attention: From Imitation and Innovation to Feeding Back
2025-06-20Machine Learning40 eqlinear RNN generative model attention
- The Derivative of msign
2025-06-13Mathematics24 eqcalculus matrix gradient muon
- Computing the Singular Value Clip mclip via msign (Part 1)
2025-06-07Mathematics14 eqiteration approximation matrix SVD muon
- Newton-Schulz Iteration for the msign Operator (Part 2)
2025-06-05Mathematics19 eqiteration approximation optimizer muon
- The Equioscillation Theorem: A Necessary and Sufficient Condition for Optimal Polynomial Approximation
2025-06-02Mathematics32 eqderivative approximation optimal analysis
- Generative Diffusion Models Chat (30): From Instantaneous Velocity to Average Velocity
2025-05-26Machine Learning24 eqdifferential equation generative model sampling diffusion
- MoE Time Travel: 5. Rethinking the Uniform Distribution
2025-05-16Machine Learning6 eqoptimization sparse MoE
- Newton-Schulz Iteration for the msign Operator (Part 1)
2025-05-11Mathematics23 eqiteration approximation optimizer muon
- The Road to Transformer Upgrades: 20. What Makes MLA Good? (Part 1)
2025-05-04Machine Learning10 eqoptimization language model generative model attention
- A Probability Inequality: Stare at It Until It Becomes Obvious!
2025-04-30Mathematics8 eqinequality probability trivially true
- The Derivative of SVD
2025-04-26Mathematics41 eqcalculus analysis matrix SVD gradient
- Transformer Upgrade Path: 19. The Second Kind of Rotary Position Embedding
2025-04-18Mathematics13 eqlanguage model attention positional encoding RoPE
- The Effective Rank of a Matrix
2025-04-10Mathematics12 eqmatrix entropy sparse low-rank
- Finding Alternatives to Normalization via Gradient Approximation
2025-04-02Mathematics14 eqfunction analysis gradient smoothness
- MoE Journey: 4. More Effort Where It's Hardest
2025-03-28Machine Learning10 eqoptimization gradient MoE dynamics
- Higher-Order MuP: A Simpler yet Smarter Spectral Condition Scaling
2025-03-24Mathematics27 eqgradient optimizer scaling law spectral norm muon MuP
- An Initial Look at MuP: Scaling Laws for Hyperparameter Transfer Across Model Sizes
2025-03-13Mathematics14 eqgradient learning rate optimizer scaling law MuP
- A Tour of MoE: 3. A Different Way to Allocate
2025-03-05Machine Learning13 eqoptimal loss function gradient MoE
- Muon Sequel: Why Did We Choose to Try Muon?
2025-02-27Machine Learning13 eqmatrix gradient optimizer spectral norm muon
- MoE Journeys: 2. It's Not Scarcity but Inequality That Should Worry Us
2025-02-21Machine Learning9 eqloss function gradient sparse MoE
- Diffusion Models Miscellany (29): Discrete Coding with DDPM
2025-02-14Machine Learning16 eqgenerative model encoding DDPM diffusion discretization
- MoE Odyssey: 1. Starting from Geometric Intuition
2025-02-08Machine Learning8 eqmodel geometry sparse MoE
- Coordinates of the Intersection of Three Spheres (Trilateration)
2025-01-28Mathematics7 eqequation geometry
- A Steady Stream of Flow: TARFLOW - Flow Models Return in Full Force?
2025-01-17Machine Learning12 eqflow model flow generative model attention
- The Road to Low-Rank Approximation (5): CUR
2025-01-12Mathematics13 eqapproximation optimal matrix low-rank
- Why is the default clipping norm for gradient clipping equal to 1?
2025-01-02Machine Learning5 eqoptimization gradient learning rate optimizer
- From Spectral Norm Gradients to a New Kind of Weight Decay
2024-12-25Machine Learning15 eqmatrix optimization gradient optimizer spectral norm
- Generative Diffusion Models Explained (28): Understanding Consistency Models Step by Step
2024-12-18Machine Learning13 eqdifferential equation generative model sampling diffusion
- Diffusion Models Chat (27): Using Step Size as a Conditioning Input
2024-12-15Machine Learning13 eqdifferential equation generative model sampling diffusion
- Muon Optimizer Appreciation: The Essential Leap from Vectors to Matrices
2024-12-10Machine Learning31 eqmatrix gradient optimizer spectral norm muon
- Adaptive Learning Rate Optimizers Viewed through Hessian Approximation
2024-11-29Mathematics17 eqoptimization gradient learning rate optimizer
- Generative Diffusion Models Explained (26): Distillation Based on Identities (Part 2)
2024-11-22Machine Learning17 eqgenerative model gradient diffusion denoising
- How does Adam's epsilon affect the learning rate Scaling Law?
2024-11-18Machine Learning18 eqgradient learning rate optimizer scaling law
- When Batch Size Increases, How Should the Learning Rate Change?
2024-11-14Machine Learning33 eqgradient learning rate optimizer scaling law
- Another VQ Trick: Adding a Linear Transformation to the Codebook
2024-11-06Machine Learning4 eqgenerative model encoding gradient discretization
- The Road to Low-Rank Approximation (IV): ID
2024-10-30Mathematics12 eqapproximation optimal matrix low-rank
- The Rotation Trick for VQ: A General Extension of the Straight-Through Gradient Estimator
2024-10-24Machine Learning6 eqgenerative model encoding gradient discretization
- Cool Papers Browser Extension Upgraded to v0.2.0
2024-10-16Machine Learningwebsite paper cool paper
- Making MathJax Formulas Auto-Scale with Window Size
2024-10-151 eqwebsite latex
- Low-Rank Approximation (III): CR
2024-10-11Mathematics22 eqapproximation optimal matrix low-rank
- The Road to Low-Rank Approximation (II): SVD
2024-10-01Mathematics29 eqapproximation optimal matrix SVD low-rank
- Softmax's Sequel: In Search of a Smooth Approximation to Top-K
2024-09-19Mathematics23 eqprobability approximation gradient smoothness
- Low-Rank Approximation (I): Pseudo-Inverse
2024-09-15Mathematics25 eqapproximation matrix low-rank
- "Building Cars Behind Closed Doors" — Some Thoughts on Multimodality (Part 3): Positional Encoding
2024-09-06Machine Learning9 eqattention positional encoding multimodal
- Why does the decoder-only LLM need positional encoding?
2024-09-016 eqlanguage model attention positional encoding
- Nearly Perfectly Resolving the Conflict Between MathJax and Marked
2024-08-26website latex paper cool paper
- Making MathJax Play Nicer with Google Translate and Lazy Loading
2024-08-15website latex paper cool paper
- Some New Attempts at "Cool Papers + On-site Search"
2024-08-12Machine Learningwebsite paper cool paper
- The Road to the Optimal Distribution: Minimization in Probability Space
2024-08-06Mathematics46 eqprobability optimization gradient diffusion
- Aligning with Full Fine-tuning! The Most Brilliant LoRA Improvement I've Seen (Part 2)
2024-07-29Machine Learning24 eqgradient optimizer low-rank LoRA
- Monarch Matrices: A Computationally Efficient Sparse-Style Matrix Factorization
2024-07-24Mathematics10 eqmatrix language model sparse low-rank
- Aligning with Full Fine-Tuning! The Most Impressive LoRA Improvement I've Seen (Part 1)
2024-07-12Machine Learning11 eqgradient optimizer low-rank LoRA
- "Building in Isolation": A Few Thoughts on Multimodal Approaches (Part 2): Autoregression
2024-07-08Machine Learning1 eqgenerative model diffusion multimodal autoregressive
- Revisiting SSM (Part 4): A New Perspective from Rational Generating Functions
2024-06-27Mathematics27 eqgenerating function linear RNN state space model
- Revisiting SSM (III): Efficient Computation of HiPPO (S4)
2024-06-20Mathematics39 eqmatrix linear RNN state space model
- The Road to Probability Distributions: A Survey of Softmax and Its Alternatives
2024-06-14Mathematics36 eqprobability analysis loss function gradient
- Revisiting SSM (II): Some Leftover Questions about HiPPO
2024-06-05Mathematics31 eqlinear difference RNN gradient state space model
- Transformer Upgrade Path: 18. The Choice Principle for RoPE's Base
2024-05-29Machine Learning14 eqinequality attention positional encoding RoPE
- Revisiting SSM (I): Linear Systems and the HiPPO Matrix
2024-05-24Mathematics33 eqdifferential equation linear RNN state space model
- The Ultimate Tug-of-War Between Cache and Performance: From MHA, MQA, GQA to MLA
2024-05-13Machine Learning12 eqoptimization language model generative model attention
- Cool Papers Update: A Simple Site Search System
2024-05-07Machine Learningwebsite paper cool paper
- Diffusion Models Revisited (25): Identity-Based Distillation (Part 1)
2024-05-01Machine Learning12 eqgenerative model gradient diffusion denoising
- Generative Diffusion Models Talk (24): Take Fewer Shortcuts, Arrive Faster
2024-04-23Machine Learningdifferential equation generative model diffusion
- Diffusion Models for Generation, Chatting Casually (Part 23): Signal-to-Noise Ratio and Large-Image Generation (Part 2)
2024-04-17Machine Learning11 equnsupervised generative model diffusion SNR
- Diffusion Models Ramble (Part 22): Signal-to-Noise Ratio and Large-Image Generation (I)
2024-04-08Machine Learning7 eqloss function generative model diffusion SNR
- Transformer Upgrade Path: 17. Some Simple Thoughts on Multimodal Positional Encoding
2024-03-29Machine Learning12 eqattention positional encoding RoPE multimodal
- Spacetime Chapter: Viewing Attention as an RNN with Quadratic Complexity
2024-03-18Mathematics2 eqlanguage model RNN attention complexity
- Fitting a One-Dimensional Probability Density Function with Fourier Series
2024-03-07Mathematics17 eqseries probability analysis approximation
- Can LoRA still be improved by using different learning rates?
2024-02-27Machine Learning8 eqgradient optimizer low-rank LoRA
- "Reinventing the Wheel": Some Thoughts on Multimodal Approaches (I): Lossless Input
2024-02-21Machine Learning2 eqgenerative model attention diffusion multimodal
- A More Convenient Way to Open Cool Papers: A Chrome Redirect Extension
2024-02-02Machine Learningwebsite paper cool paper
- Idempotent Generative Networks (IGN): A GAN That Tries to Merge Discriminator and Generator into One
2024-01-31Machine Learning10 eqGAN generative model adversarial
- Transformer Upgrade Path: 16. "Revisiting" Length Extrapolation Techniques
2024-01-26Machine Learning11 eqattention positional encoding generalization extrapolation RoPE
- The Sidetrack of Making Python's Retry Code More Elegant
2024-01-14Machine Learningprogramming code Python optimization
- Does High Local Cosine Similarity Guarantee High Global Cosine Similarity?
2024-01-09Mathematics8 eqinequality similarity paradox
- Happy New Year! A Note on the Cool Papers Development Experience
2024-01-01Machine Learningwebsite paper cool paper
- Made a Website to Help Read Papers: Cool Papers
2023-12-25Machine Learningwebsite paper cool paper
- Making Model Training a Bit More Scientific (I): Convergence of the Average Loss for SGD
2023-12-19Machine Learning24 eqinequality optimizer SGD model tuning
- Can Attention Mechanisms Really "Concentrate Attention"?
2023-12-12Machine Learning11 eqentropy sparse attention rank
- Diffusion Models Revisited (21): Speeding up ODE Sampling with the Mean Value Theorem
2023-12-07Machine Learning14 eqdifferential equation generative model diffusion
- I Found Traces of Transformer-VQ in Performer
2023-11-29Machine Learning9 eqquantization language model attention
- The Road to Upgrading Transformer: 15. Key Normalization Boosts Length Extrapolation
2023-11-20Machine Learning10 eqattention positional encoding generalization extrapolation
- VQ the Key, and Transformer Complexity Becomes Linear
2023-11-09Machine Learning10 eqquantization encoding gradient attention
- The Embarrassingly Simple FSQ: "Rounding" Outperforms VQ-VAE
2023-10-31Machine Learning10 eqgenerative model encoding gradient discretization
- Attention's Scale Factor from the Perspective of Gradient Maximization
2023-10-22Machine Learning7 eqoptimization gradient attention
- Random Tokenization Revisited: From Viterbi Sampling to a Perfect Sampling Algorithm
2023-10-16Machine Learning9 eqprobability random optimization tokenization sampling
- EMO: A Classification Loss Function Designed Around Optimal Transport
2023-10-13Machine Learning9 eqprobability optimization loss function optimal transport
- A Bit of Pretraining Goes a Long Way: Transformer's Long-Sequence Scores Can Rise a Lot!
2023-10-08Machine Learninglanguage model attention
- Mind-Blowing: Can Non-Linear RNNs Actually Be Parallelized Too?
2023-09-26Machine Learning16 eqequation iteration language model RNN
- The Minimum of a + b + c under N = ab + c in the Natural Numbers
2023-09-2016 eqoptimal problem
- A Brief Exploration of Random Tokenization: From Viterbi Decoding to Viterbi Sampling
2023-09-16Machine Learning5 eqprobability random tokenization new word discovery
- A Problem in Continuation Tasks for Language Models with Large Vocabularies, and a Countermeasure
2023-09-13Machine Learning1 eqprobability problem language model
- BytePiece: A Purer, Higher-Compression Tokenizer
2023-09-07Machine Learning5 eqtokenization unsupervised new word discovery
- Embedding Anomalies under Lion/Tiger Optimizer Training and Countermeasures
2023-08-28Machine Learning2 eqproblem gradient optimizer
- Transformer Upgrade Path: 14. When HWFA Meets ReRoPE
2023-08-24Machine Learning4 eqattention positional encoding extrapolation RoPE
- Transformer Upgrade Path: 13. Inverting Leaky ReRoPE
2023-08-14Machine Learning5 eqattention positional encoding generalization extrapolation RoPE
- Transformer Upgrade Path: 12. ReRoPE for Infinite Length Extrapolation?
2023-08-07Machine Learning17 eqattention positional encoding generalization extrapolation RoPE
- The Road to Upgrading Transformer: 11. Carrying β-ary Positions to the End
2023-07-31Machine Learning18 eqattention positional encoding generalization extrapolation RoPE
- Revisiting Shared Output Embeddings in Language Models
2023-07-20Machine Learning10 eqlanguage model initialization
- When Generative Models Run Rampant: Should the Internet Fear "Mad Cow Disease"?
2023-07-14Machine Learning2 eqgenerative model
- Transformer Upgrade Path: 10. RoPE as a β-ary Encoding
2023-07-06Machine Learning5 eqattention positional encoding generalization extrapolation RoPE
- Generative Diffusion Models Explained (XX): From ReFlow to WGAN-GP
2023-06-28Machine Learning11 eqoptimization GAN gradient diffusion
- Generative Diffusion Models Explained (Part 19): GAN as a Diffusion ODE
2023-06-24Machine Learning15 eqoptimization GAN diffusion
- Gradient Flow: Exploring the Path Toward the Minimum
2023-06-16Mathematics23 eqfunctional dynamics optimization gradient
- Naive Bayes is all you need?
2023-06-08Machine Learning13 eqlanguage model attention LLM bayesian
- Some Supplementary Notes and Analysis on the NBCE Method
2023-05-31Machine Learning7 eqlanguage model extrapolation LLM bayesian
- NBCE: Extending LLM Context Length with Naive Bayes
2023-05-23Machine Learning11 eqlanguage model extrapolation LLM bayesian
- Deriving Scaling Laws for Models from a Quantization Hypothesis
2023-05-18Machine Learning6 eqmodel analysis quantum scaling law
- Transformer Upgrade Path: 9. A New Idea for Global Length Extrapolation
2023-05-12Machine Learning4 eqattention generalization extrapolation
- How to Measure the Sparsity of Data?
2023-05-05Mathematics20 eqprobability entropy metric sparse
- Two Interesting Observations about Attention and Softmax: Robustness and Information Content
2023-04-25Mathematics5 eqinformation entropy attention
- LoRA from a Gradient Perspective: Introduction, Analysis, Speculation, and Extensions
2023-04-17Mathematics15 eqgradient optimizer low-rank LoRA
- JL Lemma and Entropy-Invariant Attention
2023-04-10Machine Learning3 eqentropy attention
- The Surprising Role of the Bias Term: RoPE + Bias = Better Length Generalization
2023-04-03Machine Learning6 eqlanguage model attention positional encoding extrapolation RoPE
- Google's New Work Attempts to "Resurrect" RNNs: Can RNNs Shine Again?
2023-03-28Machine Learning16 eqlanguage model RNN generative model attention
- FAQ on *"Why Are Current LLMs All Decoder-only Architectures?"*
2023-03-20Machine LearningQ&A language model text generation attention
- Why Do Current LLMs All Use Decoder-only Architectures?
2023-03-17Machine Learning2 eqanalysis language model text generation attention
- A Simple Scheme for Mitigating the Overconfidence of Cross-Entropy
2023-03-14Machine Learning8 eqoptimization loss function smoothness
- Tiger: An Optimizer That's "Stingy" to the Extreme
2023-03-07Machine Learning12 eqmodel optimization optimizer
- Diffusion Models Revisited (18): Score Matching = Conditional Score Matching
2023-02-28Machine Learning9 eqprobability analysis generative model diffusion
- Diffusion Models Talk (17): The General Procedure for Constructing ODEs (Part III)
2023-02-23Machine Learning17 eqprobability differential equation generative model diffusion
- Google's Newly Discovered Optimizer Lion: The "Training Lion" That Has Both Efficiency and Effectiveness
2023-02-16Machine Learning6 eqanalysis optimization optimizer
- Rambling on about Generative Diffusion Models (16): W-distance ≤ Score Matching
2023-02-14Machine Learning26 eqdifferential equation GAN generative model diffusion
- Deriving the Continuity Equation and the Fokker-Planck Equation via Test Functions
2023-02-11Mathematics23 eqprobability differential equation random diffusion
- Transformer Upgrade Path: 8. Length Extrapolation and Positional Robustness
2023-01-31Machine Learning4 eqlanguage model attention positional encoding extrapolation
- The Path to the Transformer, Part 7: Length Extrapolation and Local Attention
2023-01-12Machine Learning7 eqlanguage model attention positional encoding extrapolation
- Transformer Upgrade Path: 6. A Completeness Analysis of Rotary Position Embedding
2022-12-28Machine Learning11 eqmatrix attention positional encoding RoPE
- Generating Diffusion Models Chat (15): The General Procedure for Constructing ODEs (Part 2)
2022-12-22Machine Learning24 eqdifferential equation generative model diffusion green's function
- Diffusion Models Revisited (14): General Steps for Constructing an ODE (Part 1)
2022-12-15Machine Learning31 eqdifferential equation generative model diffusion green's function
- From Local to Global: Geodesic Distance for Semantic Similarity
2022-12-07Machine Learning1 eqriemannian geometry semantics semantic similarity
- Using the Heat Equation to Guide Self-Supervised Learning
2022-11-30Machine Learning5 eqphysics unsupervised
- Some "Model Training Strategies" Derived from the Ideas Behind the Amos Optimizer
2022-11-22Machine Learning29 eqanalysis optimization asymptotic optimizer
- CoSENT (III): A Loss Function for Interactive Similarity Models
2022-11-09Machine Learning4 eqsemantics semantic similarity contrastive learning
- Accelerating Retrieval for Interactive Similarity Models via CUR Decomposition
2022-11-02Machine Learning4 eqmatrix semantics semantic similarity
- The probability that n random points inside a circle all lie within a sector of central angle θ
2022-10-25Mathematics13 eqprobability competition random
- Generative Diffusion Models: Chapter 13 — From Universal Gravitation to Diffusion Models
2022-10-18Machine Learning12 eqgravity field theory generative model diffusion
- A Modest Attempt at the "Cross" Combinatorics Problem
2022-10-09Mathematicsproof mathematics combinatorics
- Rambling on About Generative Diffusion Models (12): Tackling the Diffusion ODE Head-On
2022-09-28Machine Learning20 eqdifferential equation generative model diffusion
- Generative Diffusion Models Explained (Part 11): The Unified Diffusion Model (Applications)
2022-09-21Machine Learning18 equnification generative model DDPM diffusion
- Generative Diffusion Models Explained (X): Unified Diffusion Models (Theory)
2022-09-14Machine Learning13 equnification generative model DDPM diffusion
- Talking About Generative Diffusion Models (IX): Conditional Control of Generation Results
2022-08-30Machine Learning24 eqprobability generative model DDPM diffusion
- Diffusion Models Revisited (VIII): Optimal Diffusion Variance Estimation (Part 2)
2022-08-18Machine Learning13 eqoptimization generative model DDPM diffusion
- Generative Diffusion Models Explained (VII): Optimal Diffusion Variance Estimation (Part 1)
2022-08-12Machine Learning16 eqoptimization generative model DDPM diffusion
- Rambling on About Generative Diffusion Models (Part 6): The ODE Formulation of the General Framework
2022-08-08Machine Learning17 eqdifferential equation generative model DDPM diffusion
- Generative Diffusion Models Explained (V): The SDE Formulation of the General Framework
2022-08-03Machine Learning27 eqdifferential equation generative model DDPM diffusion
- Random Talk on Generative Diffusion Models (Part 4): DDIM = DDPM from a Higher Vantage Point
2022-07-27Machine Learning25 eqdifferential equation generative model DDPM diffusion
- Generative Diffusion Models Explained (III): DDPM = Bayes + Denoising
2022-07-19Machine Learning18 eqprobability generative model DDPM diffusion
- An Unsuccessful Attempt: Generalizing Multi-Label Cross-Entropy to "n groups of m-class classification"
2022-07-15Mathematics8 eqoptimization loss function
- Generative Diffusion Models Explained (II): DDPM = Autoregressive VAE
2022-07-06Machine Learning10 eqVAE generative model DDPM diffusion
- A Brief Look at the "Curse of Dimensionality": The Hubness Phenomenon
2022-06-28Machine Learning2 eqdimension GAN generative model
- Ladder Side-Tuning: A "Ladder Over the Wall" for Pretrained Models
2022-06-20Machine Learning2 eqlanguage model pretraining
- Generative Diffusion Models: A Rambling Introduction (I): DDPM = Demolition + Construction
2022-06-13Machine Learning19 eqprobability generative model DDPM diffusion
- A Theoretical Flaw in Relative Position Encoding Transformers, and Some Countermeasures
2022-06-07Machine Learning5 eqlanguage model attention positional encoding
- How to Train Your Accuracy?
2022-06-01Machine Learning3 eqprobability optimization loss function
- Constructing Discrete Probability Distributions from the Perspective of Reparameterization
2022-05-25Mathematics11 eqprobability reparameterization
- When BERT-whitening Gets Hyperparameters: There's Always a Setting That Suits You
2022-05-18Machine Learning6 eqlanguage model semantics semantic similarity
- Several Inequalities for the logsumexp Operation
2022-05-10Mathematics21 eqinequality function
- A Soft-Label Version of Multi-label "Softmax + Cross-Entropy"
2022-05-07Machine Learning9 eqoptimization loss function smoothness
- Using Mixed Precision and XLA to Speed Up Training in bert4keras
2022-04-28Machine Learningmodel optimization gradient
- GAU-α: A First Taste of the Next-Generation Attention That's Faster, Better, and Cheaper
2022-04-22Machine Learning2 eqlanguage model attention pretraining
- Does Your Language Model Have "Unpredictable Words"?
2022-04-20Machine Learning12 eqlanguage model multi-task
- What Should "KL Divergence" Look Like Under GlobalPointer?
2022-04-15Mathematics7 eqloss function adversarial training NER regularization
- A Quick Derivation of Entropy-Invariant Softmax
2022-04-11Mathematics8 eqapproximation entropy attention
- I Heard That Attention Gets Along Better with Softmax~
2022-04-07Machine Learning4 eqentropy language model attention pretraining
- Why Does Pre-Norm Underperform Post-Norm?
2022-03-29Machine Learning3 eqoptimization gradient attention
- RoFormerV2: Pushing the Limits of Natural Language Understanding
2022-03-21Machine Learning5 eqlanguage model pretraining
- Why Do We Need Residuals? A Perspective from DeepNet
2022-03-19Machine Learning10 eqmodel optimization deep learning gradient
- Does the Gated Attention Unit (GAU) still need Warmup?
2022-03-11Machine Learning9 eqmodel optimization attention
- What exactly makes it so hard to train a 1000-layer Transformer?
2022-03-09Machine Learning17 eqoptimization gradient attention
- Exponentiated Gradient Descent + Meta-Learning = Adaptive Learning Rate
2022-03-03Mathematics12 eqoptimization gradient optimizer
- FLASH: Possibly the Most Interesting Efficient Transformer Design in Recent Times
2022-02-25Machine Learning8 eqlanguage model generative model attention
- GPLinker: Joint Event Extraction Based on GlobalPointer
2022-02-21Machine Learning2 eqNLP information extraction NER
- Multi-Task Learning Ramblings (III): Ranking Priorities
2022-02-14Machine Learning13 eqduality deep learning loss function gradient multi-task
- Multi-Task Learning Ramblings (II): The Business of Gradients
2022-02-08Machine Learning23 eqduality deep learning loss function gradient multi-task
- GPLinker: Joint Entity-Relation Extraction Based on GlobalPointer
2022-01-30Machine Learning7 eqNLP information extraction NER
- Efficient GlobalPointer: Fewer Parameters, Better Results
2022-01-25Machine Learning9 eqmodel NLP NER
- Multi-Task Learning Musings (I): In the Name of Loss
2022-01-18Machine Learning13 eqdeep learning loss function multi-task
- CoSENT (Part 2): How Big Is the Gap Between Representation-based and Interaction-based Matching?
2022-01-12Machine Learning3 eqsemantics semantic similarity contrastive learning
- CoSENT (I): A More Effective Sentence Embedding Approach than Sentence-BERT
2022-01-06Machine Learning10 eqsemantics semantic similarity contrastive learning
- SquarePlus: Perhaps the Simplest-to-Compute Smooth Approximation of ReLU
2021-12-29Mathematics8 eqfunction approximation analysis
- Entropy Normalization for Probability Distributions
2021-12-24Mathematics7 eqprobability entropy
- From Entropy Invariance: A Look at the Scale Operation in Attention
2021-12-21Machine Learning14 eqprobability entropy attention
- Seq2Seq + Prefix Tree: A New Paradigm for Retrieval Tasks (Using KgCLUE as an Example)
2021-12-17Machine Learning4 eqcode semantics Keras similarity
- An Inequality Between Input Gradient Penalty and Parameter Gradient Penalty
2021-12-11Mathematics12 eqinequality optimization gradient generalization
- Variational Autoencoders (VIII): Estimating Sample Probability Density
2021-12-09Machine Learning6 eqprobability variational VAE generative model
- Blowing up over a "miracle paper" with data pulled out of thin air
2021-12-04sentiment model
- MLM and MAE Through the Lens of Dropout: Some New Insights
2021-11-29Machine Learning12 eqmodel probability analysis optimization
- ChildTuning: Trying to Add Dropout to Gradients?
2021-11-22Machine Learning8 eqmodel optimization gradient
- WGAN New Approach: Enforcing the L-constraint via Gradient Normalization
2021-11-15Machine Learning4 equnsupervised GAN generative model
- Model Optimization Chat: Why Is BERT's Initialization Standard Deviation 0.02?
2021-11-08Machine Learning6 eqmodel analysis optimization gradient
- With bert4keras in hand, I've got my baseline covered: CLUE benchmark code
2021-10-31Machine Learning4 eqmodel code Keras
- CAN: A Simple Post-Processing Trick to Boost Classification Performance via Prior Distributions
2021-10-22Machine Learning9 eqmodel probability analysis technique
- Rethinking the Dimension-Averaging Strategy for Non-Square Matrices in Initialization
2021-10-18Machine Learning7 eqmodel optimization gradient
- Using the Dirac Function to Construct Smooth Approximations of Non-Smooth Functions
2021-10-10Mathematics15 eqfunction approximation analysis smoothness
- Questions and Communications Regarding the Originality of WhiteningBERT
2021-10-09sentiment model work
- On the Usability of the Dimensionality Formula "n > 8.33 log N"
2021-09-27Machine Learningdimension entropy word vector
- The Astonishing Johnson-Lindenstrauss Lemma: Applications
2021-09-24Machine Learning4 eqmodel analysis dimension machine learning
- The Remarkable Johnson–Lindenstrauss Lemma: Theory
2021-09-17Machine Learning24 eqmodel analysis dimension machine learning
- NSP, a Once-Disdained Pretraining Task, Delivers Impressive Zero-Shot Results
2021-09-10Machine Learningunsupervised language model NLP template
- Globally Shuffling Hundreds of Gigabytes of Files with Limited Memory (Python)
2021-09-08Machine Learningprogramming Python
- From the Triangle Inequality to Margin Softmax
2021-09-01Machine Learning9 eqloss function similarity
- Gradient Accumulation Hidden Inside Momentum: Fewer Update Steps, Better Results?
2021-08-24Machine Learning17 eqmodel analysis gradient optimizer
- A Brief Discussion on Transformer Initialization, Parameterization and Normalization
2021-08-17Machine Learning17 eqmodel optimization gradient attention
- Linear Transformers Are Probably Not the Model You're Waiting For
2021-08-09Machine Learning5 eqmodel matrix attention
- Transformer Upgrade Path: 5. Standard Attention as an Infinite-Dimensional Linear Attention
2021-08-06Machine Learning13 eqlanguage model attention kernel method
- FlatNCE: Is Floating-Point Error the Real Reason Contrastive Learning Struggles with Small Batches?
2021-07-26Machine Learning5 eqoptimization loss function contrastive learning
- Linear Models Through a Probabilistic Lens: Does Logistic Regression Have an Analytical Solution?
2021-07-22Mathematics25 eqmodel probability optimization
- Using Open-Source Human-Annotated Data to Enhance RoFormer-Sim
2021-07-19Machine Learning4 eqlanguage model generative model text generation
- Two Multivariate Normal Distributions: KL Divergence, Bhattacharyya Distance and Wasserstein Distance
2021-07-08Mathematics50 eqprobability matrix optimization
- Dropout Twice Again! This Time It Achieves SOTA on Supervised Tasks
2021-07-01Machine Learning16 eqoptimization loss function adversarial training
- UniVAE: A Single-Model, Multi-Scale VAE Based on Transformer
2021-06-29Machine Learningvariational unsupervised VAE attention
- Can Contrastive Learning Use Gradient Accumulation?
2021-06-17Machine Learning6 eqmodel optimization gradient
- SimBERTv2 is here! RoFormer-Sim, a model that combines retrieval and generation
2021-06-11Machine Learning7 eqlanguage model generative model text generation
- An orthogonal matrix that transforms one unit vector into another
2021-06-05Mathematics14 eqtransform vector matrix
- Can We Losslessly Scale Up a Transformer Model? (Part 1)
2021-06-02Machine Learning19 eqmodel optimization attention
- A Roundup of Some Recent Non-Transformer Work
2021-05-24Machine Learning6 eqmodel optimization language model attention
- Variational Autoencoders (VII): VAE on a Sphere (vMF-VAE)
2021-05-17Machine Learning14 eqvariational unsupervised VAE generative model
- Transformer Upgrade Path: 4. Two-Dimensional Rotary Position Embedding
2021-05-10Machine Learning29 eqcomplex number matrix attention positional encoding RoPE
- GlobalPointer: A Unified Approach to Nested and Non-Nested NER
2021-05-01Machine Learning15 eqmodel NLP NER
- Is SimCSE Still SOTA for Chinese Tasks? Some Supplementary Experiments
2021-04-26Machine Learning3 eqlanguage model semantics semantic similarity contrastive learning
- Transformer Upgrade Path: 3. From Performer to Linear Attention
2021-04-22Machine Learning8 eqlanguage model attention
- Sohu Text Matching: A Multi-task Baseline Based on Conditional LayerNorm
2021-04-16Machine Learninglanguage model competition semantic similarity
- Which unsupervised semantic similarity method is best? We ran a fairly comprehensive evaluation
2021-04-11Machine Learning8 eqlanguage model semantics semantic similarity
- P-tuning: Automatically Constructing Templates to Unleash the Potential of Language Models
2021-04-03Machine Learning2 eqlanguage model NLP
- Transformer Upgrade Path: 2. Rotary Position Embedding That Draws on the Best of Both Worlds
2021-03-23Machine Learning25 eqcomplex number language model attention positional encoding RoPE
- WGAN's success may have nothing to do with the Wasserstein distance
2021-03-15Machine Learning4 eqoptimization GAN generative model
- Transformer Upgrade Path: 1. Tracing the Origins of Sinusoidal Positional Encoding
2021-03-08Mathematics14 eqcomplex number analysis attention positional encoding
- Short-Text Matching Baseline: Attempting Pretrained Models on Anonymized Data
2021-03-05Machine Learninglanguage model semantics semantic similarity
- T5 PEGASUS: Open-Sourcing a Chinese Generative Pretrained Model
2021-03-03Machine Learning6 eqlanguage model text generation attention
- 【Text via Search】⋅(4) Composing Sentences from Given Words via Insertion, Deletion, and Replacement
2021-02-25Machine Learning7 eqtext generation sampling discrete optimization MCMC
- Nyströmformer: A Linearized Attention Scheme Based on Matrix Decomposition
2021-02-16Machine Learning13 eqmatrix language model attention
- How Does a Binarized Word Embedding Model End Up Connected to Fruit Flies?
2021-02-092 eqNLP word vector NLP
- The Transformer Positional Encodings That Have Kept Researchers Racking Their Brains
2021-02-03Machine Learning19 eqcomplex number attention positional encoding
- A Theoretical Analysis Attempt of the Repetition Problem in Seq2Seq Decoding
2021-01-26Machine Learning15 eqmatrix language model text generation decoding
- [Text extracted through search] · (III) BERT-Based Text Sampling
2021-01-22Machine Learningtext generation sampling discrete optimization MCMC
- 【Searching for Text】· (2) From MCMC to Simulated Annealing
2021-01-14Machine Learning13 eqtext generation sampling discrete optimization MCMC
- You Might Not Need BERT-flow: A Linear Transformation Rivaling BERT-flow
2021-01-11Mathematics12 eqlanguage model semantics flow semantic similarity
- [Text Sampled Out]. (I) From Text Generation to Search Sampling
2021-01-07Machine Learning11 eqtext generation sampling discrete optimization MCMC
- SPACES: An "Extract-then-Generate" Approach to Long-Text Summarization (CAIL Competition Summary)
2021-01-01Machine Learning5 eqtext generation sparse text summarization
- RealFormer: Moving the Residual Connection onto the Attention Matrix
2020-12-24Machine Learning5 eqgradient attention
- Optimization Algorithms from a Dynamical Perspective (VII): SGD ≈ SVM?
2020-12-21Machine Learning9 eqdifferential equation dynamics optimization kernel method
- Mitchell Approximation: Turning Multiplication into Addition, with an Error Bound of 1/9
2020-12-14Mathematics13 eqmodel algorithm optimization
- From a Dynamical Perspective on Optimization Algorithms (VI): Why Doesn't SimSiam Collapse?
2020-12-11Machine Learning10 eqdynamics optimization unsupervised
- Hierarchical Decomposition of Position Encodings, Enabling BERT to Handle Ultra-Long Text
2020-12-04Machine Learning4 eqmodel optimization attention
- Performer: Linearizing Attention's Complexity via Random Projections
2020-12-01Machine Learning14 eqoptimization attention
- The even-order Taylor expansion of exp(x) at x=0 is always positive
2020-11-24Mathematics8 eqderivative probability analysis
- Jumping on the bandwagon to play with the largest Chinese GPT2 model currently available (bert4keras)
2020-11-20Machine Learninglanguage model text generation attention
- On the Vanishing/Exploding Gradient Problem of RNNs, Once More
2020-11-13Machine Learning16 eqmodel optimization deep learning gradient
- When GPT Meets Chinese Chess: After Writing Articles and Solving Problems, How About a Game of Chess?
2020-11-11Machine Learning2 eqChinese chess language model attention
- The chart-topping T5 model — now you can play with it in Chinese
2020-11-06Machine Learning4 eqlanguage model text generation attention
- Before Using ALBERT and ELECTRA, Make Sure You Really Understand Them
2020-10-29Machine Learninglanguage model attention
- TeaForN: Giving Teacher Forcing a Bit More "Foresight"
2020-10-27Machine Learning5 eqoptimization language model text generation
- What Grade Level Has BERT Reached? Using Seq2Seq to Tackle Elementary School Math Word Problems
2020-10-19Machine Learning4 eqlanguage model text generation
- How to Split Off a Validation Set That's Closer to the Test Set
2020-10-16Machine Learning6 eqmodel probability optimization sampling
- From a Dynamical Systems Perspective on Optimizers (V): Why Shouldn't the Learning Rate Be Too Small?
2020-10-10Machine Learning10 eqdifferential equation dynamics gradient optimizer
- Must It Be GPT3? No — BERT's MLM Can Do Few-Shot Learning Too
2020-09-27Machine Learning10 equnsupervised language model NLP
- Speed Up Without Losing Accuracy: A Word-Granularity Chinese WoBERT
2020-09-18Machine Learning8 eqlanguage model attention
- The Convergent Paths of Policy Gradient and Zeroth-Order Optimization
2020-09-15Mathematics23 eqoptimization gradient optimizer reinforcement learning
- Variational Autoencoders (VI): An Attempt to Understand VAEs from a Geometric Perspective
2020-09-10Machine Learning5 eqvariational unsupervised VAE generative model
- Building a DialoGPT from Scratch: An LM-Based Generative Multi-Turn Dialogue Model
2020-09-07Machine Learning4 eqlanguage model text generation attention
- Revisiting Class Imbalance: Connecting Weight Adjustment and Loss-Engineering Tricks
2020-08-31Machine Learning13 eqoptimization loss function smoothness
- The Principle of Minimum Entropy (VI): How Should We Choose the Dimensionality of Word Embeddings?
2020-08-20Machine Learning17 eqentropy word vector minimum entropy
- L2 Regularization May Not Be as Good as We Thought — "Weight Scale Shift" Might Be to Blame
2020-08-14Machine Learning10 eqmodel optimization deep learning
- Modifying the Transformer Architecture to Design a Faster, Better MLM Model
2020-08-07Machine Learning4 eqlanguage model attention
- Do We Really Need to Drive the Training Loss All the Way to Zero?
2020-07-31Machine Learning5 eqoptimization deep learning loss function generalization
- BERT that learns to ask questions: building QA pairs end-to-end from passages
2020-07-25Machine Learninglanguage model text generation
- Mitigating Class Imbalance via Mutual Information
2020-07-19Machine Learning9 eqoptimization mutual information loss function
- BERT-of-Theseus: A Model Compression Method Based on Module Replacement
2020-07-17Machine Learning3 eqmodel attention model compression
- The Mighty NVAE: Never Say VAE-Generated Images Are Blurry Again
2020-07-10Machine Learning6 eqvariational VAE generative model
- Exploring Linear Attention: Does Attention Really Need a Softmax?
2020-07-04Machine Learning10 eqmodel text generation attention
- Integrated Gradients: A Novel Method for Neural Network Visualization
2020-06-28Machine Learning7 eqintegral gradient visualization
- From Sampling to Optimization: A Unified Perspective on Differentiable and Non-Differentiable Optimization
2020-06-23Mathematics19 eqoptimization gradient optimizer sampling
- How to Deal with the "It Just Won't Stop" Problem in Seq2Seq?
2020-06-16Machine Learning4 eqlanguage model text generation decoding
- Unsupervised Word Segmentation and Syntactic Parsing! Turns Out BERT Can Be Used Like This
2020-06-10Machine Learning5 equnsupervised new word discovery
- Why Gradient Clipping Accelerates Training: A Concise Analysis
2020-06-05Mathematics12 eqoptimization gradient
- Ramblings on Generalization: From Random Noise and Gradient Penalties to Virtual Adversarial Training
2020-06-01Machine Learning20 eqprobability GAN adversarial training generalization
- Google's New Work Synthesizer: We Still Don't Understand Self-Attention Well Enough
2020-05-25Machine Learning9 eqlanguage model attention
- Having Your Cake and Eating It Too: SimBERT, a Model That Combines Retrieval and Generation
2020-05-18Machine Learninglanguage model generative model text generation
- From EMD to WMD to WRD: Computing Similarity Between Text Vector Sequences
2020-05-13Machine Learning8 eqoptimal optimization semantics linear programming
- A Brief Look at the AdaX Optimizer (with Open-Source Implementation)
2020-05-11Machine Learning4 eqoptimizer
- Variational Autoencoders (V): VAE + BN = A Better VAE
2020-05-06Machine Learning12 eqvariational unsupervised VAE generative model
- The memory-saving recomputation trick now has a Keras version too
2020-04-29Machine Learningmodel deep learning Keras
- Generalizing "Softmax + Cross-Entropy" to Multi-Label Classification Problems
2020-04-25Machine Learning11 eqoptimization loss function smoothness
- EAE: Autoencoder + BN + Maximum Entropy = Generative Model
2020-04-20Machine Learning13 eqmaximum entropy entropy unsupervised generative model
- Breaking through the Bottleneck: Building a Stronger Transformer
2020-04-13Machine Learning4 eqprobability deep learning attention
- bert4keras in Hand, Baseline in Sight: Baidu LIC2020
2020-04-02Machine Learningmodel Keras attention
- Where do GELU's two elementary-function approximations come from?
2020-03-26Mathematics15 eqapproximation analysis
- A Brief Analysis of the AdaFactor Optimizer (with Open-Source Implementation)
2020-03-23Machine Learning19 eqanalysis Keras optimizer
- Now You Can Play with Chinese GPT2 in Keras (GPT2_ML)
2020-03-16Machine Learninglanguage model NLP text generation attention
- A Brief Analysis of the Exposure Bias Phenomenon in Seq2Seq, and Some Countermeasures
2020-03-09Machine Learning21 eqlanguage model text generation adversarial training
- A Brief Introduction to Adversarial Training: Meaning, Methods, and Reflections (with Keras Implementation)
2020-03-01Machine Learning13 eqGAN Keras adversarial training generalization
- Already used CRF? Time to get acquainted with the faster MEMM
2020-02-24Machine Learning8 eqmodel probabilistic graphical model CRF
- Designing GANs: Another GAN Production Workshop
2020-02-13Machine Learning22 eqcalculus GAN generative model
- Your CRF Layer's Learning Rate Might Not Be High Enough
2020-02-07Machine Learning6 eqmodel probabilistic graphical model CRF
- Dropping the Constraint, Strengthening the Model: Boosting albert's Performance with One Line of Code
2020-01-29Machine Learning8 eqlanguage model attention
- Understanding Model Parameter Initialization from a Geometric Perspective
2020-01-16Mathematics4 eqmodel probability geometry optimization
- Self-Orthogonality Module: A Plug-and-Play Kernel Orthogonalization Module
2020-01-12Machine Learning9 eqmodel
- Triple Extraction with bert4keras
2020-01-03Machine Learning2 eqlanguage model information extraction
- "Non-autoregressive" is no slouch either: MLM-based reading comprehension QA
2019-12-26Machine Learning2 eqQ&A language model generative model text generation
- Conditional Text Generation Based on Conditional Layer Normalization
2019-12-14Machine Learninglanguage model text generation attention
- The universal seq2seq: reading comprehension QA based on seq2seq
2019-12-05Machine LearningQ&A language model text generation
- Cascading Rejection: A Simple Yet Effective Way to Improve GAN Performance
2019-12-01Machine Learning3 eqgeometry GAN generative model
- Six Optimizer Variants: A Brief Introduction and Implementation
2019-11-25Machine Learning5 eqPython Keras optimizer
- The distribution of the angle between two random vectors in n-dimensional space
2019-11-13Mathematics13 eqprobability analysis
- JoSE: Word and Sentence Embeddings on the Sphere
2019-11-11Machine Learning10 eqgeometry NLP word vector NLP
- Keras: The Gold Standard for TensorFlow
2019-11-06Machine LearningKeras
- From Denoising Autoencoders to Generative Models
2019-10-31Machine Learning12 eqgenerative model encoding gradient denoising
- When Can the Speedup of Multiprocessing Exceed 1?
2019-10-27Machine Learningprogramming Python
- The Minimum Entropy Principle (V): "Layer by Layer" — Community Detection and Clustering
2019-10-19Machine Learning15 eqentropy clustering unsupervised minimum entropy
- What Does BN Actually Do? A "Reinventing the Wheel" Analysis
2019-10-11Machine Learning16 eqmodel optimization neural network
- "Making Keras Cooler!": Techniques for Reusing Layers and Models
2019-09-29Machine Learning4 eqmodel Keras
- From Language Models to Seq2Seq: Transformer Is Like an Actor — It's All About the Mask
2019-09-18Machine Learning3 eqlanguage model NLP text generation attention
- Rewriting the Previous New-Word Discovery Algorithm: Faster and Better
2019-09-09Machine Learning4 eqtokenization unsupervised NLP new word discovery
- Post-mortem on Baidu's Entity Linking Competition: Behavior Modeling and Entity Linking
2019-09-03Machine Learningmodel NLP NER
- I built my own bert4keras
2019-08-27Machine Learninglanguage model NLP Keras attention
- HSIC: An Interesting Approach to Judging Correlation
2019-08-26Mathematics54 eqprobability mutual information kernel method
- Open-sourcing a Keras implementation of the DGCNN reading-comprehension QA model
2019-08-20Machine Learningmodel Q&A
- Seq2Seq with Bidirectional Decoding
2019-08-09Machine Learning5 eqmodel NLP Keras text generation
- Implementing Two Optimizers in Keras: Lookahead and LazyOptimizer
2019-07-30Machine LearningKeras optimizer
- For the Sake of Efficiency: From Standard Attention to Sparse Attention
2019-07-27Machine Learning1 eqmodel sparse attention
- Thoughts on Whether Two Elliptical Sheets Can Be Glued into a Solid
2019-07-21Mathematics17 eqproof equation curve
- "Making Keras Cooler!": Layers within Layers, and Masks
2019-07-16Machine Learning24 eqKeras
- Trading Time for Performance: A Keras Gradient Accumulation Optimizer
2019-07-08Machine LearningKeras gradient optimizer
- A Bert-based NL2SQL Model: A Concise Baseline
2019-06-29Machine Learninglanguage model competition SQL attention
- A Concise Introduction to VQ-VAE: Quantized Autoencoders
2019-06-24Machine Learning13 equnsupervised generative model encoding discretization
- A brief note on unbiased and biased estimators
2019-06-19Mathematics8 eqstatistics probability estimation
- When Bert Meets Keras: Perhaps the Simplest Way to Get Started with Bert
2019-06-18Machine Learninglanguage model competition information extraction attention
- Rambling on Reparameterization: From the Normal Distribution to Gumbel Softmax
2019-06-10Mathematics17 eqprobability algorithm optimization reparameterization
- A Lightweight Information Extraction Model Based on DGCNN and Probabilistic Graphs
2019-06-03Machine Learning3 eqmodel competition probabilistic graphical model information extraction
- ON-LSTM: Expressing Hierarchical Structure with Ordered Neurons
2019-05-28Machine Learning15 eqmodel deep learning unsupervised NLP
- On Function Smoothing: Differentiable Approximations to Non-Differentiable Functions
2019-05-20Mathematics14 eqderivative function approximation smoothness
- GAN Models from an Energy Perspective (III): Generative Models = Energy Models
2019-05-10Machine Learning8 eqprobability energy optimization generative model
- From the Dynamical Systems Perspective on Optimization Algorithms (IV): The Third Stage of GAN
2019-05-03Machine Learning19 eqdifferential equation dynamics GAN generative model optimizer
- "Making Keras Cooler!": Intermediate Variables, Weight Moving Averages, and Process-Safe Generators
2019-04-28Machine Learning2 eqmodel optimization Keras
- From DCGAN to SELF-MOD: A Survey of GAN Architecture Development
2019-04-19Machine Learning7 eqmodel GAN generative model
- Sharing an Unsupervised Approach to Mining Domain-Specific Vocabulary
2019-04-10Machine Learningtokenization unsupervised vocabulary new word discovery
- Sharing: Drawing a 3×3×3 Magic Cube with LaTeX+MathJax
2019-03-28Mathematics2 eqfun magic square sharing
- The Reversible ResNet in the Flow Series: An Extreme Aesthetic of Brute Force
2019-03-21Machine Learning19 eqanalysis flow model flow generative model
- "Making Keras Cooler!": Per-Layer Learning Rates and Free Gradient Manipulation
2019-03-10Machine Learning3 eqmodel Keras gradient learning rate
- O-GAN: A Simple Modification That Turns a GAN Discriminator into an Encoder!
2019-03-06Machine Learning10 equnsupervised GAN generative model encoding
- Constructing an Explicit, Always-Invertible Matrix
2019-03-01Mathematics7 eqmatrix determinant
- A Brief Introduction to the Non-Adversarial Generative Model GLANN
2019-02-26Machine Learning16 eqprobability generative model
- Cleverly Cutting Off Gradients: Implementing a GAN with a Single Loss
2019-02-22Machine Learning5 eqGAN generative model Keras gradient
- Appreciating the Identity det(exp(A)) = exp(Tr(A))
2019-02-18Mathematics20 eqanalysis matrix determinant
- GAN Models from the Energy Perspective (Part 2): GAN = "Analysis" + "Sampling"
2019-02-15Machine Learning31 eqprobability energy GAN generative model
- GAN Through the Lens of Energy (I): GAN = "Digging Pits" + "Jumping into Pits"
2019-01-30Machine Learning6 eqprobability energy GAN generative model
- "Making Keras Cooler!": Freeform Outputs and Flexible Normalization
2019-01-27Machine Learning1 eqmodel loss function Keras
- From Wasserstein Distance and Duality Theory to WGAN
2019-01-20Mathematics36 eqduality optimization GAN generative model
- A Couplet Robot Based on CNN and Sequence Labeling
2019-01-14Machine LearningNLP text generation
- From a Dynamical Systems Perspective on Optimization Algorithms (III): A More Holistic View
2019-01-08Mathematics11 eqdifferential equation dynamics numerical computation optimizer
- [Reading List] Some Important Recent GAN Papers
2018-12-26Machine Learninglearning GAN generative model
- Viewing Optimization Algorithms from a Dynamical Systems Perspective (II): Adaptive Learning Rate Algorithms
2018-12-20Mathematics45 eqdifferential equation dynamics numerical computation optimizer
- BiGAN-QP: A Simple and Clean Encoding & Generative Model
2018-12-10Machine Learning4 equnsupervised GAN generative model encoding
- The Minimum Entropy Principle (IV): "Birds of a Feather" — From the Library to Word Embeddings
2018-12-02Machine Learning13 eqentropy clustering word vector unsupervised minimum entropy
- From Variational Encoding and Information Bottleneck to the Normal Distribution: On the Importance of Forgetting
2018-11-27Machine Learning19 eqprobability variational mutual information VAE
- A GAN That Needs No Lipschitz Constraint and Yet Doesn't Suffer From Vanishing Gradients—Interested?
2018-11-20Machine Learning22 eqprobability GAN generative model metric
- WGAN-div: The Unsung Hero That Patched Up WGAN
2018-11-07Machine Learning11 eqGAN generative model metric
- RSGAN: The "Turing Test" Idea in Adversarial Models
2018-10-22Machine Learning17 eqprobability unsupervised GAN generative model
- Revisiting the Determinant of Non-Square Matrices
2018-10-16Mathematics9 eqvector matrix determinant
- Variational Autoencoders = Minimizing the Prior Distribution + Maximizing Mutual Information
2018-10-10Machine Learning3 eqvariational mutual information VAE
- Lipschitz Constraints in Deep Learning: Generalization and Generative Models
2018-10-07Machine Learning81 eqGAN generative model generalization spectral norm
- Mutual Information in Deep Learning: Unsupervised Feature Extraction
2018-10-02Machine Learning46 eqmaximum entropy unsupervised mutual information
- f-GAN Introduction: A Production Workshop for GAN Models
2018-09-29Machine Learning61 eqvariational GAN inference generative model
- Thin Water, Long Flow: f-VAEs, the Marriage of Glow and VAEs
2018-09-21Machine Learning57 eqVAE flow model flow generative model
- Variational Autoencoders (IV): A One-Shot Clustering Scheme
2018-09-17Machine Learning16 eqclustering unsupervised VAE generative model
- "Making Keras Cooler!": A Niche Topic — Custom Optimizers
2018-09-08Machine Learning4 eqKeras optimizer
- Getting Hands-On with Keras: Seq2Seq for Automatic Title Generation
2018-09-01Machine Learning8 eqmodel NLP Keras text generation
- A Steady Stream of Flow: RealNVP and Glow - The Inheritance and Sublimation of Flow Models
2018-08-26Machine Learning20 eqprobability flow model flow generative model
- The Endless Flow of NICE: Basic Concepts and Implementation of Flow Models
2018-08-11Machine Learning36 eqprobability flow model flow generative model
- "Making Keras Cooler!": Elegant Layers and Fancy Callbacks
2018-08-06Machine Learningmodel deep learning loss function Keras
- Sentence Similarity Model Based on GRU and AM-Softmax
2018-07-29Machine Learning22 eqsemantics loss function similarity
- Unifying Generative Models via Variational Inference (VAE, GAN, AAE, ALI)
2018-07-18Machine Learning129 eqvariational deep learning inference
- From SamplePairing to mixup: A Magical Regularization Term
2018-07-07Machine Learning4 eqmodel
- Viewing Optimizers from the Perspective of Dynamics (I): From SGD to Momentum Acceleration
2018-06-27Mathematics48 eqdifferential equation dynamics numerical computation optimizer
- The Illusory Divide, the Hidden Unity: RNNs and ODEs — An Introduction to "Fancy" RNNs
2018-06-23Machine Learning16 eqdifferential equation recursion RNN
- A Miscellany on "Noise Contrastive Estimation": The Beauty of an Indirect Route
2018-06-13Mathematics28 eqprobability word vector estimation
- An NLP Library Based on the Minimum Entropy Principle: nlp zero
2018-05-31Machine LearningPython unsupervised minimum entropy
- The Minimum Entropy Principle (III): "Flying Elephant Fording the River" — Sentence Templates and Language Structure
2018-05-30Machine Learningentropy unsupervised NLP minimum entropy
- A Concise Introduction to Conditional Random Fields (CRF), with a Pure Keras Implementation
2018-05-18Machine Learning24 eqmodel probabilistic graphical model Keras CRF
- Efficient Apriori Algorithm in NumPy
2018-05-10Machine LearningPython data mining association analysis
- A Conv1D-Based Spectral Classification Model (1D Sequence Classification)
2018-05-02Machine Learningmodel astronomy spectrum
- The Principle of Minimum Entropy (Part 2): "Decisive Cutting" for Vocabulary Construction
2018-04-24Machine Learning40 eqentropy unsupervised NLP minimum entropy
- The Minimum Entropy Principle (I): The Foundations of Unsupervised Learning
2018-04-18Machine Learning4 eqentropy unsupervised NLP minimum entropy
- CNN-Based Reading Comprehension QA Model: DGCNN
2018-04-15Machine Learning24 eqmodel Q&A deep learning
- Variational Autoencoders (III): Why Does This Approach Actually Work?
2018-04-03Machine Learning28 eqprinciple unsupervised VAE generative model
- Variational Autoencoders (Part 2): Starting from a Bayesian Perspective
2018-03-28Mathematics50 eqprobability unsupervised VAE generative model
- A Poetry-Writing Robot Based on CNN and VAE: Composing Poems from Random Noise
2018-03-24Machine Learningliterature VAE generative model text generation
- Variational Autoencoders (I): So That's What It's About
2018-03-18Machine Learning22 eqvariational unsupervised VAE generative model
- From Maximum Likelihood to the EM Algorithm: A Unified Way of Understanding
2018-03-15Mathematics46 eqprobability optimization clustering
- Three Flavors of Capsules: Matrix Capsules with EM Routing
2018-03-02Machine Learning50 eqdeep learning clustering capsule
- Another New Year Feast: From K-Means to Capsule
2018-02-12Machine Learning38 eqdeep learning clustering capsule
- Sharing a slide deck: Fancy Natural Language Processing
2018-01-23Machine Learningdeep learning NLP
- Cutting Through the Mist: A Delicious Feast of Capsules
2018-01-23Machine Learning28 eqdeep learning clustering capsule
- Enhancing Typecho's Search Functionality
2018-01-09Machine Learningwebsite Python
- A Light Reading of "Attention is All You Need" (Introduction + Code)
2018-01-06Machine Learning9 eqmodel deep learning attention
- From Hard Truncation and Soft Weighting to Focal Loss
2017-12-25Machine Learning28 eqmodel deep learning loss function
- The Method of Characteristics for First-Order PDEs
2017-12-07Mathematics87 eqequation differential equation
- CRF In A Nutshell
2017-11-25Machine Learning20 eqmodel probabilistic graphical model CRF
- A More Elegant Word Embedding Model (VI): Code, Sharing, and Closing Remarks
2017-11-19Machine Learningword vector GloVe
- A More Elegant Word Embedding Model (V): Some Interesting Results
2017-11-19Machine Learningword vector GloVe semantics
- A More Elegant Word Embedding Model (IV): Solving the Model
2017-11-19Machine Learningoptimization word vector GloVe
- A More Distinctive Word Embedding Model (III): A Model that Describes Relatedness
2017-11-19Machine Learning4 eqword vector GloVe
- A More Elegant Word Embedding Model (II): Modeling Language
2017-11-19Machine Learningword vector mutual information GloVe
- A More Elegant Word Vector Model (I): Simpler GloVe
2017-11-19Machine Learningword vector GloVe
- On the Design of Activation Functions in Neural Networks
2017-10-26Machine Learning21 eqneural network
- What Do Training, Validation, and Test Sets Really Mean?
2017-10-14Machine Learningmodel deep learning
- Image Classification with Fine-Tuning (Baidu's Dog-Breed Classification Competition)
2017-10-13Machine Learningclassification image deep learning
- From Markov Processes to the Master Equation (A Derivation)
2017-10-06Mathematics33 eqprobability master equation
- Evaluating the Importance of Inputs in RNN Models
2017-09-10Machine Learning6 eqdeep learning
- Back to School! Let's Play Fill-in-the-Blank (iFLYTEK Cup)
2017-09-03Machine Learningneural network machine learning competition
- A Baseline for Fashion MNIST (MobileNet 95%)
2017-08-27Machine Learningneural network deep learning
- A GAN toy example on Fashion-MNIST
2017-08-26Machine Learningdeep learning GAN generative model
- 【Note to self】On Dropout
2017-08-08Machine Learningdeep learning
- 【The Amazing Word2Vec】6. Keras Version of Word2Vec
2017-08-06Machine Learningword vector word2vec Keras
- Tencent Captcha Recognition Based on Xception (with Samples and Code)
2017-07-24Machine Learningimage deep learning dataset
- Custom Complex Loss Functions in Keras
2017-07-22Machine Learning12 eqmodel deep learning loss function Keras
- The Big Pitfall of Accidental Deletion on Linux, and Simple Recovery Tricks
2017-07-16Machine Learninglinux technique
- Reference Solutions to *Introduction to Commutative Algebra*
2017-07-03Mathematicsalgebra
- The Art of Mutual Sparring: From Scratch Straight to WGAN-GP
2017-06-08Machine Learning54 eqprobability unsupervised GAN generative model
- Generic Crawler Exploration (Part 3): Results and Code
2017-06-07Machine Learningwebsite crawler
- General-Purpose Crawler Exploration (II): Applying It to Forum Crawling
2017-06-06Machine Learning2 eqwebsite crawler
- General-Purpose Web Scraping (I): A Scraper for General Websites
2017-06-06Machine Learning18 eqwebsite crawler
- 【The Amazing Word2Vec】5. Word2Vec in Tensorflow
2017-05-27Machine Learning8 eqdeep learning word vector word2vec
- How to Scrape a Website: A Hands-On Tutorial for Scraping Baidu Baike
2017-05-17Machine Learningcrawler corpus
- Notes on a Semi-Supervised Sentiment Analysis Attempt
2017-05-04Machine Learningdeep learning text mining
- 【The Incredible Word2Vec】4. Different Kinds of "Similarity"
2017-05-01Machine Learning8 eqword vector word2vec mutual information
- [The Incredible Word2Vec] 3. Extracting Keywords
2017-04-07Machine Learning8 eqword vector word2vec language model
- 【The Amazing Word2Vec】 2. A Pretrained Model
2017-04-03Machine Learning2 eqword vector word2vec language model
- 【The Amazing Word2Vec】 1. Mathematical Principles
2017-04-02Machine Learningword vector word2vec language model
- Text Sentiment Classification (IV): A Better Loss Function
2017-03-30Machine Learning10 eqdeep learning text mining loss function
- Gradient Descent and the EM Algorithm: Born of the Same Root, Part of the Same Lineage
2017-03-23Machine Learning33 eqprobability optimization clustering
- Teddy Cup Pre-Competition Training: A "Leisurely Chat" on Data Mining and Modeling
2017-03-14Machine Learningdata mining
- Chinese Word Segmentation Series: 8. A Better New Word Discovery Algorithm
2017-03-11Machine Learning2 eqtokenization vocabulary new word discovery
- [Chinese Word Segmentation Series] 7. Deep Learning Segmentation with Just a Dictionary!
2017-03-06Machine Learning2 eqtokenization NLP unsupervised new word discovery
- SVD Decomposition (III): Is Even Word2Vec Just an SVD?
2017-02-23Machine Learning6 eqdeep learning SVD word vector
- Python Multiprocessing Techniques
2017-02-19Machine Learningprogramming Python
- SVD Decomposition (II): Why Does SVD Imply Clustering?
2017-01-26Machine Learning8 eqclustering SVD
- SVD Decomposition (I): Autoencoders and Artificial Intelligence
2017-01-15Machine Learning10 eqdeep learning SVD intelligence
- 【Chinese Word Segmentation Series】 6. Chinese Word Segmentation Based on a Fully Convolutional Network
2017-01-13Machine Learningdeep learning tokenization NLP
- The Dirac Function: Series Approximation
2017-01-11Mathematics44 eqseries approximation
- A Smoothing Formula Based on the Forgetting Hypothesis
2017-01-07Mathematics26 eqstatistics corpus smoothing
- Fetching and Processing the Chinese Wikipedia Corpus
2017-01-06Machine Learningwiki language corpus
- [Memo] Several Ideas for Breaking Out of Nested Loops in Python
2016-12-19Machine LearningPython memo
- End-to-End Tencent CAPTCHA Recognition (46% accuracy)
2016-12-14Machine Learning2 eqimage deep learning OCR end-to-end
- What Word Vectors and Embeddings Are Really About
2016-12-03Machine Learning6 eqdeep learning NLP
- Aspect-Based Sentiment Analysis with Bidirectional GRU and Language Models
2016-12-01Machine Learningmodel Python deep learning NLP
- A Lightweight Deep Learning Tokenizer: NNCWS v0.1
2016-11-29Machine Learningtokenization NLP
- Three Visits to Shredded Paper Restoration: CNN-Based Shredded Paper Restoration
2016-11-25Machine LearningPython modeling image deep learning
- Scientific Spaces "WeChat Group | Chatbot" Online Testing
2016-11-24Machine Learningwebsite test
- Why Is the Lebesgue Integral Better Than the Riemann Integral?
2016-11-16Mathematics6 eqintegral analysis measure
- [A Gentle Introduction to Exterior Differentiation] 7. The Power of the Method Computationally
2016-11-11Mathematics48 eqcomputation riemannian geometry exterior differentiation
- [A Gentle Introduction to Exterior Calculus] 6. Differential Geometry
2016-11-07Mathematics40 eqgeometry riemannian geometry exterior differentiation
- 【A Gentle Introduction to Exterior Differentiation】5. Geometric Meaning
2016-11-06Mathematics26 eqintegral geometry exterior differentiation
- [A Brief Introduction to Exterior Differentiation] 4. Differentials Aren't So Small
2016-11-05Mathematics14 eqvector symmetry exterior differentiation
- [A Brief Introduction to Exterior Differentiation] 3. Orthogonal Frames
2016-11-05Mathematics26 eqsymmetry exterior differentiation
- 【A Brief Introduction to Exterior Differentiation】2. The Power of Antisymmetry
2016-11-04Mathematics22 eqsymmetry exterior differentiation outer product
- 【A Brief Introduction to Exterior Calculus】1. Introduction and Motivation
2016-11-04Mathematicsvector exterior differentiation
- 【Understanding Riemannian Geometry】8. Geometry Everywhere (Geometrizing Mechanics)
2016-11-0236 eqmechanics geometry action riemannian geometry
- [Understanding Riemannian Geometry] 7. The Gauss–Bonnet Formula
2016-10-21Mathematics32 eqgeometry riemannian geometry
- Understanding Riemannian Geometry: 6. Counting and Computing Curvature (Python)
2016-10-19Mathematics18 eqgeometry curvature Python riemannian geometry permutation and combination
- 【Understanding Riemannian Geometry】5. Riemann Curvature
2016-10-18Mathematics22 eqgeometry curvature riemannian geometry
- 【Understanding Riemannian Geometry】4. Connections and Covariant Derivatives
2016-10-16Mathematics24 eqgeometry analysis riemannian geometry
- Understanding Riemannian Geometry: 3. Geodesics
2016-10-15Mathematics24 eqgeometry riemannian geometry calculus of variations
- [Understanding Riemannian Geometry] 2. From the Pythagorean Theorem to the Riemannian Metric
2016-10-14Mathematics30 eqtransform geometry riemannian geometry
- Understanding Riemannian Geometry, Part 1: A Geometric Path
2016-10-14Mathematicsgeometry riemannian geometry
- Chinese Word Segmentation Series: 5. Unsupervised Segmentation Based on Language Models
2016-09-12Machine Learning18 eqtokenization NLP unsupervised new word discovery
- seq2seq Core Entity Recognition Based on Bidirectional LSTM and Transfer Learning
2016-09-06Machine LearningPython NLP recognition NER
- Moving into Sun Yat-sen University's South Campus, Wrestling with the Campus Network
2016-09-05Machine LearningOpenWrt router
- [Chinese Word Segmentation Series] 4. Sequence-to-Sequence Character Tagging Based on Bidirectional LSTM
2016-08-22Machine Learningprobability Python tokenization NLP
- [Chinese Word Segmentation Series] 3. The Character-Tagging Approach and the HMM Model
2016-08-19Machine Learning16 eqprobability Python tokenization HMM NLP
- [Chinese Tokenization Series] 2. New Word Discovery Based on Segmentation
2016-08-18Machine Learning2 eqtokenization unsupervised NLP new word discovery
- 【Chinese Word Segmentation Series】 1. Fast Segmentation Based on the Aho-Corasick Automaton
2016-08-17Machine Learning6 eqdynamic programming AC automaton tokenization NLP vocabulary
- Two Impressive Python Libraries: tqdm and retry
2016-08-13Machine LearningPython
- Perturbation methods for difference equations
2016-08-04Mathematics72 eqperturbation difference equation
- From Boosting to Neural Networks: Mountains as Mountains?
2016-07-01Machine Learning20 eqneural network boosting sentiment classification
- Text Sentiment Classification (III): To Tokenize or Not to Tokenize
2016-06-29Machine Learning2 eqPython deep learning text mining
- A Brief Exploration of OCR Technology: 9. Sharing the Code (Final)
2016-06-26Machine Learningcode image OCR
- OCR: A Brief Exploration — 8. Overall Evaluation
2016-06-26Machine Learningmodel image OCR
- A Brief Exploration of OCR Technology: 7. Language Models
2016-06-26Machine Learning10 eqmodel OCR language dynamic programming
- OCR Technology, a Brief Exploration: 6. Optical Recognition
2016-06-25Machine Learning2 eqneural network deep learning OCR text
- A Brief Exploration of OCR Techniques: 5. Text Segmentation
2016-06-24Machine Learningimage OCR text
- A Brief Exploration of OCR Techniques: 4. Text Localization
2016-06-24Machine Learning6 eqimage OCR text search
- A Brief Exploration of OCR Techniques: 3. Feature Extraction (2)
2016-06-18Machine Learning6 eqimage OCR feature text
- A Brief Exploration of OCR Technology: 3. Feature Extraction (1)
2016-06-18Machine Learning12 eqimage OCR feature clustering text
- A Brief Exploration of OCR Technology: 2. Background and Assumptions
2016-06-17Machine Learningimage data mining OCR text
- A Brief Exploration of OCR Technology: 1. Overview
2016-06-17Machine Learningimage data mining OCR
- Path Integrals Series: 5. Examples and Overview
2016-06-09Mathematics16 eqdifferential equation differential path integral finance
- Path Integral Series: 4. Stochastic Differential Equations
2016-06-09Mathematics44 eqdifferential equation path integral random
- Path Integrals Series: 3. The Path Integral
2016-06-02Mathematics52 eqdifferential equation path integral feynman
- Path Integrals Series: 2. The Random Walk Model
2016-05-30Mathematics42 eqpath integral random walk
- Path Integral Series: 1. My Graduation Thesis
2016-05-30Mathematicspath integral
- Stirling's Formula and Asymptotic Series
2016-04-15Mathematics34 eqseries integral analysis
- 【Memo】Setting Up a Raspberry Pi 3 as a Wireless Router
2016-04-12Machine Learninglinux router
- The Implicit Solution of a Nonlinear Difference Equation
2016-04-09Mathematics54 eqnonlinear difference equation asymptotic
- *Quantum Mechanics and Path Integrals* — Solutions to Exercises V0.5
2016-04-01Mathematicspath integral feynman
- [Euler's Mathematics] A Summary of the Bernoulli Series and Related Series
2016-03-20Mathematics40 eqseries euler mathematics
- Sharing Campus Resources via SSH Dynamic Port Forwarding (With Practical Tips)
2016-03-07Machine LearningOpenWrt router
- Openwrt Automatically Scanning for WiFi and Connecting as a Relay
2016-03-06Machine LearningOpenWrt router
- Fun Problem: How to Programmatically List All Subsets of a Set
2016-03-04Machine LearningPython set
- The Intuitive Origin of Entropy and Some Clever Uses
2016-02-20Mathematics4 eqinformation entropy
- The Extremal Principle for Estimating Integrals — A Beginner's Version of the Variational Principle
2016-02-15Mathematics30 eqinequality integral extremum
- Tinkering with the Jiwei Router on New Year's Eve: SSH Reverse Proxy
2016-02-07Machine Learningholiday network OpenWrt router
- -*- coding:utf-8 -*-
2016-01-20Machine LearningPython crawler
- When Big Data Enters the Kitchen: Letting Big Data Teach You to Cook!
2016-01-18Machine LearningPython kitchen data mining hobby
- "Entropy" Speaks: From Entropy and the Maximum Entropy Principle to the Maximum Entropy Model (Part 3)
2015-12-20Mathematics20 eqmodel probability maximum entropy entropy
- "Entropy" Cannot Be Left Alone: From Entropy, the Maximum Entropy Principle, to the Maximum Entropy Model (Part 2)
2015-12-11Mathematics48 eqprobability extremum maximum entropy entropy
- Life is short, I use Python!
2015-12-06Machine LearningPython data mining
- Making Sense of "Entropy": From Entropy, the Maximum Entropy Principle, to Maximum Entropy Models (I)
2015-12-01Mathematics30 eqprobability maximum entropy entropy
- The Distribution of ARXIV Math Papers: Analysis of PDEs Comes Out on Top!
2015-11-13Machine Learning2 eqPython data mining
- Let's Grab a Soda, Friends! The Fun "Bottle Exchange" Problem
2015-10-28Mathematics14 eqfun competition
- Information Entropy Methods for New Word Discovery: Theory and Implementation
2015-10-26Machine LearningPython maximum entropy vocabulary new word discovery
- Running a Python script on your phone on a schedule
2015-10-21Machine LearningPython crawler
- The Area Enclosed by a Closed Curve: A New Trick
2015-08-30Mathematics48 eqintegral transform
- A Diagrammatic Technique for the Series Expansion of exp(1/2 t² + xt)
2015-08-13Mathematics10 eqseries diagram
- Text Sentiment Classification (II): Deep Learning Models
2015-08-04Machine LearningPython deep learning machine learning text mining
- On "Does 0.999... Equal 1?"
2015-07-21Mathematics2 eqfunction analysis
- In Plain Terms: Models, and Picking Mangoes
2015-07-15Machine Learningmodel machine learning
- Efficient Apriori Algorithm Implementation with Pandas
2015-07-02Machine LearningPython data mining association analysis
- Text Sentiment Classification (I): Traditional Models
2015-06-22Machine Learning14 eqPython machine learning data mining text mining
- Chatting About Neural Networks and Deep Learning
2015-06-06Machine Learning6 eqneural network deep learning machine learning
- The Victory of Nonsense: Introducing Operators into Series Summation
2015-05-26Mathematics26 eqlimit series operator
- A record of crawling Taobao/Tmall review data
2015-05-06Machine Learningwebsite crawler
- In Search of a Smooth Maximum Function
2015-05-02Mathematics28 eqfunction extremum smoothness
- Gaussian-type integrals: perturbative expansion (III)
2015-04-26Mathematics34 eqintegral perturbation perturbation
- The Cauchy Proposition: Stare at It Until It Becomes Obvious!
2015-04-19Mathematics22 eqlimit analysis trivially true
- The Sampling Theorem: Reconstructing an Entire Function from Finitely Many Points
2015-04-16Mathematics14 eqintegral Fourier sampling
- A fun limit problem: bounding things however you like
2015-03-28Mathematics24 eqinequality limit analysis
- A neat physical derivation of Heron's formula
2015-03-27Mathematics16 eqphysics area
- The Parallel-Lines Problem You've Never Really Thought About
2015-03-17Mathematicsgeometry axiom
- Perturbative Expansion of Gaussian-type Integrals (II)
2015-03-07Mathematics16 eqintegral perturbation perturbation asymptotic series
- Starting from a Series Problem Kontsevich Wrote on a Blackboard
2015-02-27Mathematics28 eqseries integral
- Perturbative Expansion of Gaussian-Type Integrals (I)
2015-02-14Mathematics24 eqintegral perturbation perturbation asymptotic series
- The Multiplicative Group of a Finite Prime Field is Cyclic
2015-01-20Mathematics8 eqprime number group theory field
- The Lebesgue Dominated Convergence Theorem
2015-01-16Mathematics14 eqinequality integral
- When Probability Meets Complex Analysis: From the Binomial Distribution to the Poisson Distribution
2015-01-13Mathematics18 eqprobability generating function
- Transforming Coordinates with the Calculus of Variations
2015-01-0644 eqdifferential equation analysis variational action
- The Marvelous Trick: Computing the Volume of an n-Dimensional Ball
2014-12-23Mathematics38 eqcalculus integral analysis
- Decomposing a Polynomial into a Sum of Two Irreducible Polynomials
2014-12-22Mathematics18 eqalgebra polynomial decomposition
- A Year-Late Model: Revisiting Shredded Paper Restoration
2014-12-186 eqcode Python modeling image
- A Two-Species Competition Model: LaTeX + Python
2014-12-1512 eqdifferential equation analysis modeling qualitative
- The Gamma Function's Road Through the Fourier Transform
2014-12-0834 eqcomplex number Fourier functional equation
- Polynomials Whose Value Is Always an Integer
2014-12-04Mathematics12 eqnumber theory difference
- Sine series and cosine series
2014-12-03Mathematics20 eqseries trigonometric function complex number
- The Infinite Decomposition of a Force and the Green's Function Method
2014-11-2438 eqmechanics differential equation feynman
- A Peculiar Closed-Form Formula: Quadratic Nonlinear Recurrences
2014-11-12Mathematics38 eqanalysis construction nonlinear
- There Are Only Four Finite-Dimensional Division Algebras Over the Real Numbers
2014-11-12Mathematics12 eqalgebra matrix ring theory
- There Are Only Two Groups of Order 4 and Order 6
2014-10-30Mathematics10 eqgroup theory construction classification
- Using GMP (gmpy2) in Python
2014-10-28Mathematicsnumber theory Python
- The Art of Operators: Difference, Differentiation, and Bernoulli Numbers
2014-10-27Mathematics20 eqoperator operator difference
- Starting from Fermat's Last Theorem (12): Revisiting the Tangent Line Method
2014-10-25Mathematics6 eqgeometry number theory Diophantine equation fermat's last theorem rational point
- From Fermat's Last Theorem, Continued (11): Rational Points and the Chord-Tangent Method
2014-10-24Mathematics20 eqgeometry number theory Diophantine equation fermat's last theorem rational point
- Set Partitions and Bell Numbers
2014-10-12Mathematics24 eqgenerating function partition set
- From Fermat's Last Theorem (Part 10): x^3+y^3=z^3+w^3
2014-10-10Mathematics28 eqnumber theory Diophantine equation fermat's last theorem
- A Few "Simple" Proofs Concerning the Cardinality of Sets
2014-10-01Mathematics12 eqproof set
- A bijection from the set of real numbers to the set of irrational numbers
2014-09-22Mathematics16 eqinfinity function set construction
- Cantor-Bernstein Theorem (with an Explicit Bijection!)
2014-09-19Mathematics12 eqinfinity function set construction
- Generating Functions and the Partitioning of Integers
2014-09-16Mathematics16 eqgenerating function generating function partition combinatorics
- From Fermat's Last Theorem, Part 9: n=3
2014-09-01Mathematics20 eqnumber theory Diophantine equation fermat's last theorem
- From Fermat's Last Theorem Onwards (VIII): Eisenstein Integers
2014-08-30Mathematics6 eqnumber theory fermat's last theorem
- From Fermat's Last Theorem, Part 7: Fermat's Sum of Two Squares Theorem
2014-08-23Mathematics14 eqprime number number theory fermat's last theorem
- Starting from Fermat's Last Theorem (VI): n=4 (2)
2014-08-19Mathematics32 eqnumber theory Diophantine equation fermat's last theorem
- Starting from Fermat's Last Theorem (V): n=4
2014-08-19Mathematics28 eqnumber theory Diophantine equation fermat's last theorem
- Starting from Fermat's Last Theorem (Part 4): Unique Factorization Domains
2014-08-17Mathematics12 eqnumber theory fermat's last theorem decomposition ring theory
- Starting from Fermat's Last Theorem (III): Gaussian Integers
2014-08-16Mathematics6 eqcomplex number number theory fermat's last theorem
- On Fermat's Last Theorem, Continued (Part 2): Pythagorean Triples
2014-08-15Mathematics6 eqnumber theory Diophantine equation fermat's last theorem
- Starting from Fermat's Last Theorem (I): Background
2014-08-15Mathematicsnumber theory Diophantine equation fermat's last theorem
- The Beauty of Primes 2: A Proof of Bertrand's Postulate
2014-08-09Mathematics24 eqprime number number theory
- The Beauty of Primes 1: The Product of All Primes
2014-07-30Mathematics22 eqprime number number theory
- The powerful integer sequence website OEIS
2014-07-17Mathematics2 eqnumber theory integer
- *New Understandings of Matrices 6*: Why Do Only Square Matrices Have Determinants?
2014-07-15Mathematics12 eqvector matrix linear determinant
- Machine Proofs of Homogeneous Polynomial Inequalities (Difference Substitution)
2014-07-06Mathematics28 eqproof inequality symmetry
- The General Solution of Pythagorean Triples and Its Generalizations
2014-07-01Mathematics26 eqcomplex number number theory integer
- Project Euler 454: Conquering the "Arena" in Five Days
2014-06-27Mathematics12 eqprime number number theory Python optimization
- Systems of Linear Differential Equations: Finding the General Solution from Particular Solutions
2014-06-18Mathematics36 eqintegral differential equation symmetry
- Using PyPy to Improve Python Script Execution Efficiency
2014-06-11prime number Python
- Two Million: The Sum of Primes Below It vs. The Sum of the First That Many Primes
2014-06-10Mathematicsprime number number theory Python
- When Probability Meets Complex Variables: Random Walks and Path Integrals
2014-06-04Mathematics10 eqpath integral random random walk
- When Probability Meets Complex Analysis: The Basic Formula of Random Walks
2014-04-30Mathematics14 eqprobability transform generating function random walk
- Fourier Transform: All It Takes Is Wild Imagination?
2014-04-25Mathematics30 eqseries integral transform complex number Fourier
- When Probability Meets Complex Analysis: Analytic Probability
2014-04-25Mathematics24 eqprobability complex number generating function
- Automated Reasoning for Sudoku
2014-04-21Mathematicslogic reasoning number programming code algorithm
- Fun Puzzle: The Ant Racing an Elastic Rope
2014-04-0916 eqfun
- Complex-Number Representation of the Curvature of Plane Curves
2014-03-04Mathematics32 eqcurvature complex number analysis differential geometry
- The Derivative of a Determinant
2014-02-28Mathematics15 eqcalculus analysis linear determinant
- Flip Into a New Dimension and Solve the Integral!
2014-02-25Mathematics16 eqintegral physics dimension
- The Common Tangent Circle of Three Tangent Circles: A Supplement
2014-01-30Mathematicscompass and straightedge construction geometry inversion
- The Common Tangent Circle of Three Mutually Tangent Circles
2014-01-27compass and straightedge construction geometry inversion
- The Numbers of Geometry and the Geometry of Numbers: A Brief Exploration of Hypercomplex Numbers
2014-01-11Mathematicsalgebra geometry complex number matrix
- The Matrix Form of the Uncertainty Principle
2014-01-0516 eqinequality quantum mechanics matrix
- Describing Rotations in Three-Dimensional Space with Matrices
2013-12-28Mathematics33 eqrotation matrix 3D quaternion
- Term Paper: "Clever Applications of Euler-Style Mathematics to Sequences and Series"
2013-12-26Mathematicsseries euler mathematics sequence
- Cross Products in High-Dimensional Space and Their Geometric Meaning
2013-12-26Mathematics20 eqgeometry matrix determinant high dimension
- Volume and Hadamard's Inequality
2013-12-26Mathematics21 eqinequality geometry matrix determinant
- "A New Understanding of Matrices 5": Volume = Determinant
2013-12-25Mathematics2 eqalgebra geometry matrix determinant
- Using the Discriminant of a Quadratic Equation to Test Positive Definiteness
2013-12-24Mathematics20 eqequation matrix quadratic form positive definite
- Definite Integrals of Powers of Trigonometric Functions
2013-12-05Mathematics14 eqintegral trigonometric function
- Lie Symmetry Methods for Solving Differential Equations (II)
2013-11-26Mathematicsintegral differential equation symmetry Lie group
- The Lie Symmetry Method for Solving Differential Equations (Part 1)
2013-10-29Mathematicsintegral differential equation symmetry Lie group
- Basic Skills in Mathematics, Problems 23–24 (Part II)
2013-09-27Mathematics20 eqcompetition differential equation art
- Basic Skills in Mathematics 23, 24 (Part I)
2013-09-26Mathematics17 eqcompetition differential equation art
- A Mathematical Trivium
2013-09-26Mathematicsmathematics competition
- One-Man Mathematical Modeling: Shredded Paper Reconstruction
2013-09-22software code modeling
- [Euler-style Mathematics] Finding a Rigorous Answer
2013-09-09Mathematics12 eqintegral euler mathematics sequence
- A Trick in the Calculus of Variations and Its "Misuse"
2013-07-30Mathematics18 eqvariational action
- A New Attempt at the Elementary Representation of Homogeneous Symmetric Polynomials
2013-07-05Mathematics2 eqalgebra symmetry polynomial
- When Matlab Meets Newton's Method
2013-05-22Mathematicsequation software approximation
- The Most Powerful Criterion for Convergence of Positive-Term Series?
2013-05-17Mathematics18 eqseries conjecture convergence
- A Brief Analysis of the "Pick 15" Game
2013-04-24Mathematicsprogramming game theory strategy
- The Fourth Wave: 2^29360741-1 Is Not Prime!
2013-04-15Mathematicsprime number network
- 2^29365451-1 is not prime
2013-04-14Mathematicsprime number network
- Feynman's Trick (8): Evaluating the Gaussian Integral
2013-04-14Mathematics20 eqintegral feynman
- 2^29365247-1 is also not a prime number!
2013-04-09Mathematicsprime number network
- 2^29363731-1 Is Not Prime!
2013-04-08Mathematicsprime number network
- Feynman's Trick for Integrals (7): A Synthesis of Euler's Mathematics
2013-03-27Mathematics22 eqintegral euler mathematics feynman
- Feynman's Trick (6): Two Exercises from a Textbook
2013-03-24Mathematics28 eqintegral trigonometric function symmetry feynman
- Feynman's Integration Method (5): The Legacy of Euler-style Mathematics
2013-03-24Mathematics18 eqintegral euler mathematics feynman functional
- Slight Perturbations — An Introduction to Perturbation Methods (3)
2013-03-07Mathematics20 eqdifferential equation approximation perturbation perturbation
- [Q&A] How Many Digits Are There?
2013-02-21Mathematics10 eqnumber number theory linear game
- Slight Perturbations — An Introduction to Perturbation Methods (2)
2013-02-06Mathematics17 eqapproximation perturbation perturbation
- Binary Representation of Decimal Fractions
2013-02-05Mathematics6 eqmathematics number theory
- [Problem Solved] The Shortest Distance on a Hyperbola
2013-02-04Mathematics8 eqconic section reader
- A Reader's Solution: The Locus of Midpoints of Fixed-Length Chords of an Ellipse
2013-02-02Mathematics42 eqellipse trajectory reader
- A Gentle Perturbation — An Introduction to Perturbation Methods (1)
2013-01-16Mathematics14 eqquantum mechanics approximation perturbation perturbation
- The Strange Dirac Function
2013-01-14Mathematics23 eqquantum mechanics integral function
- An Attempt to Simplify Quadratic Curves Using Complex Numbers
2013-01-02Mathematics16 eqcurve complex number conic section quadratic form
- Simplifying Quadratic Forms via Matrices (Handling the Parabolic Case with Infinitesimal Perturbation)
2012-12-25Mathematics61 eqconic section matrix linear quadratic form
- On Understanding "Differentials"
2012-12-148 eqcalculus derivative
- Operators and Linear ODEs (Part 2)
2012-11-30Mathematics20 eqdifferential equation linear operator
- Operators and Linear Ordinary Differential Equations (Part 1)
2012-11-30Mathematics34 eqdifferential equation linear operator
- "New Understanding of Matrices, Part 4": On Similar Matrices
2012-11-11Mathematics2 eqalgebra matrix linear
- Understanding Matrices 3: A Few Words on Determinants
2012-11-04Mathematicsalgebra matrix linear
- *Rethinking Matrices, Part 2*: What Is a Matrix?
2012-10-31Mathematics4 eqalgebra geometry matrix linear
- "A New Understanding of Matrices, Part 1": What Is a Matrix?
2012-10-29Mathematics18 eqalgebra matrix linear
- Share: Meng Yan's "Understanding Matrices"
2012-10-22reprint algebra matrix linear
- A Brief Discussion on the Goldbach Conjecture, Part 1
2012-10-06Mathematics2 eqprime number number theory Goldbach conjecture Python
- Getting Started with the Math Software Scilab
2012-09-28Mathematicsprogramming code math software development Scilab
- Two Elegant Proofs of the AM-GM Inequality
2012-09-26Mathematics8 eqinequality
- Mathematics During Military Training — The Number of People Who Shake Hands an Odd Number of Times
2012-09-22Mathematicsnumber theory university graph theory
- Complex Analysis Study 1: Revealing the Connection Between Differentiation and Integration
2012-08-02Mathematics6 eqcomplex number analysis complex analysis
- An "Unsolved Mystery": Why Is the Midpoint Rectangle Rule Never Taught?
2012-07-20Mathematics8 eqintegral analysis error
- A Chord of Fixed Length inside an Ellipse (the Circle-Transformation Method)
2012-07-06Mathematics12 eqellipse trajectory
- A brilliant way to prove the exterior angle sum of a polygon!
2012-07-03Mathematicsgeometry appreciation
- A Fixed-Length Chord Inside a Parabola
2012-06-3010 eqtrajectory potential energy balance stability
- The Feynman Integral Trick — Differentiation Under the Integral Sign (4)
2012-06-26Mathematics16 eqintegral differential
- Paving a Road for a Square-Wheeled Bicycle
2012-06-24Mathematics24 eqorbit trajectory appreciation
- Feynman's Trick — Differentiation Under the Integral Sign (3)
2012-06-23Mathematics22 eqintegral differential
- The Feynman Integration Trick — Differentiation Under the Integral Sign (2)
2012-06-12Mathematics24 eqintegral differential
- Which Is Larger: the Exponential Function or Its Expansion?
2012-03-18Mathematics4 eqexponent function
- 2012 "Beiyou Alliance" Independent Admission Exam — Mathematics
2012-02-12Mathematics8 eqcompetition geometry number theory
- [Euler's Mathematics] The Prime Number Theorem and Its Refinement
2011-11-19Mathematics18 eqprime number euler mathematics
- [Euler's Mathematics] The Sum of Reciprocals of Primes
2011-11-19Mathematics14 eqprime number euler mathematics
- [Euler Mathematics] The Riemann Zeta Function
2011-11-18Mathematics20 eqprime number function number theory euler mathematics
- [Euler Mathematics] The Face-Vertex-Edge Formula for Convex Polyhedra
2011-11-17Mathematicsgeometry euler mathematics topology
- The 2011 National High School Mathematics Competition
2011-10-23competition
- [Euler's Mathematics] Two Proofs That There Are Infinitely Many Primes
2011-10-02Mathematics12 eqprime number number theory euler mathematics
- Guangdong Preliminary Round of the Mathematics Competition: The Probability of Forming a Triangle
2011-09-12Mathematics2 eqholiday probability competition triangle appreciation
- Halving a Square with Triangles
2011-08-29Mathematics10 eqlimit ellipse curve
- Can the area of a rational right triangle be an integer?
2011-08-21Mathematics4 eqprime number prime number conjecture integer rational number
- A "Physical Proof" of Symmetric Polynomial Inequalities
2011-08-13Mathematics30 eqinequality IMO symmetry polynomial
- IMO 42-1 — I Can Do Geometry Too!
2011-07-30Mathematics8 eqcompetition geometry IMO farming
- The Grain-Gathering Problem (1)
2011-07-25Mathematics12 eqoptimal
- Some Little-Known Facts About e, i, π...
2011-07-25Mathematics8 eqformula appreciation
- Integrals of Powers of Trigonometric Functions
2011-07-22Mathematics20 eqintegral trigonometric function power
- [Correction] An Elegant Proof of a Classic Inequality
2011-07-20Mathematics12 eqinequality competition IMO
- A Problem About Integer-Sided Triangles
2011-07-194 eqequation number theory Diophantine equation integer
- The Radical Expression for cos 1°
2011-06-26Mathematics12 eqfunction trigonometric function
- Combining vectors with complex numbers: curves of constant curvature (1)
2011-06-19Mathematics10 eqvector curvature complex number
- The Optimal Shape Model for Mushrooms
2011-04-308 eqmodel nature optimal variational evolution
- Symmetry and Algebraic Equations
2011-04-29Mathematics14 eqequation algebra symmetry group theory
- Memo: Elliptic Coordinates and Complex Trigonometric Functions
2011-04-10Mathematics12 eqcoordinate ellipse trigonometric function complex number
- A Historical Mystery — Did Liu Hui Use Extrapolation?
2011-03-12Mathematics20 eqmystery circumference extrapolation method recursion
- [Update] "Degenerating" Vector Multiplication to Complex Numbers
2011-02-04Mathematics8 eqvector complex number
- Curve Equation of a Three-Link Linkage Device
2011-01-08Mathematics18 eqequation curve trajectory vector point mass method creativity
- The Series *Natural Extrema* — 8. Extremum Analysis
2010-12-26Mathematics20 eq2010 extremum analysis variational 2011
- *Natural Extremes* Series — 7. The Catenary Problem
2010-12-26Mathematics8 eqgravity curve potential energy extremum
- The Nature of Extremes Series — 6. Solving the Brachistochrone
2010-12-10Mathematics16 eqcurve optics extremum
- The Natural Extremes Series — 5. The Story of the Brachistochrone
2010-12-09Mathematicsflash attention curve extremum challenge
- The "Extremes in Nature" Series — 4. The Fermat Point Problem
2010-11-28Mathematics8 eqmechanics optics extremum optimal
- "Extrema in Nature" Series — 3. The Equilibrium Axiom
2010-11-28Mathematicspotential energy balance extremum nature
- "Extrema in Nature" Series — 2. Fermat's Principle
2010-11-27Mathematics6 eqrefraction reflection optics extremum nature principle
- *Natural Extrema* Series — 1. Preface
2010-11-27Mathematicsphysics extremum nature
- Police Chasing a Thief, Chasing a Cow, Missile Tracking
2010-11-06Mathematics20 eqdifferential equation curve missile
- This Week's Insights into Differential Equations
2010-11-06Mathematics4 eqdifferential equation
- Power series whose coefficients are powers of the natural numbers
2010-10-16Mathematics6 eqseries natural number power generating function
- Appreciating an Image — I Heart Math
2010-10-07Mathematicspicture
- Online Version of "Complete Table of Integral Formulas"
2010-10-06Mathematicswebsite integral
- The "Vectors" Series — 5. Plane Vector Differential Equations and Complex Numbers
2010-10-03Mathematics16 eqdifferential equation vector complex number
- Series Summation — Approximating Infinite Series
2010-09-10Mathematics38 eqseries summation infinity
- Quaternions and Their Deep Connection to Vectors
2010-08-27Mathematicsvector complex number
- Are "User Reviews" Reliable?
2010-08-26probability
- The "Vectors" Series — 4. Turning the World Upside Down (Vectors, Complex Numbers, Polar Coordinates)
2010-08-23Mathematics16 eqcoordinate rotation vector complex number
- A mysterious and terrible-looking graphic
2010-08-12Mathematicsgeometry space graphics
- Cubic Equation Root Finder (VB Program + Source Code, an "Amateur's" Humble Work)
2010-08-09Mathematicsequation root finding programming
- The Trigonometric Solution of Cubic Equations
2010-08-08Mathematics21 eqequation root finding trigonometric function
- So How Much Do We Really Know About Centroids (Centers of Mass)?
2010-07-26Mathematics4 eqrotation centroid barycenter potential energy
- Given the midpoints of a pentagon, construct the pentagon
2010-07-25Mathematicspolygon compass and straightedge construction
- The Mysterious Circle — the "Six-Point Circle" of a Triangle (with an added method)
2010-07-24Mathematics2 eqcompass and straightedge construction circle triangle collinearity
- The *Vector* Series — 2. Radius of Curvature
2010-07-18Mathematics14 eqvelocity vector circumference curvature acceleration
- The Immense Power of "Directed Line Segments"
2010-06-27Mathematicsvector vector geometry
- Mathematical Magic — A Beautiful Approximation
2010-05-29Mathematics2 eqirrational number approximation
- Misconceptions in Solving Inequalities...
2010-05-02Mathematics10 eqinequality
- The Ultimate Algorithm for Solving Equations Numerically
2010-04-04Mathematics8 eqequation series function numerical algorithm iteration taylor series
- *Equations and the Universe*: The Comings and Goings of the Two-Body Problem (Part 1)
2010-03-20Mathematics48 eqmechanics differential equation two-body problem orbit kepler
- (Original) Solving Equations by the Tangent-Parabola Method
2010-03-06Mathematics12 eqequation function numerical algorithm zero point iteration curve
- Proof that "an n-th degree equation has n roots"
2010-02-27Mathematics4 eqequation algebra
- MathPlayer 2.2 Released, Everyone Please Upgrade!
2010-02-13Mathematicsformula software
- The Formula for Rotating a Function's Graph (A Lesson in "Taking Things for Granted")
2010-02-09Mathematics20 eqformula reflection function rotation
- The Infinite Exponential Tower That Shoots Straight Up to the Sky
2010-02-06Mathematics2 eqexponent equation infinity
- 400+ Math E-books (for Download)
2010-02-04reprint book
- On the Exact Law of Free-Fall Motion (Part 2)
2010-01-0912 eqgravity free fall differential equation gravity
- On the Proof That e Is Irrational
2009-10-17Mathematics6 eqproof irrational number
- On the Convergence Criterion for Alternating Series
2009-10-06Mathematics6 eqseries
- Proof of the Existence of a Ruler-and-Compass Construction for the Regular 17-gon
2009-09-20Mathematics20 eqproof polygon compass and straightedge construction
- A problem that could show up anywhere from elementary school to high school
2009-09-20Mathematics4 eqproof inequality exponent logarithm
- Calculus Study (Part 2): Derivatives
2009-09-12Mathematics14 eqcalculus derivative limit
- The Math Love Letter Written by a High School Senior (Respect)
2009-09-06Mathematicsreprint mathematics
- Solving the Quartic Equation by Radicals (A Plain-Language Version)
2009-09-06Mathematics2 eqequation radical algebra
- The Ruler-and-Compass Construction of the Regular 17-gon
2009-08-28Mathematics2 eqregular polygon compass and straightedge construction flash attention
- A General Proof of the Arithmetic-Geometric Mean Inequality
2009-08-24Mathematics6 eqproof inequality
- A Limit Proof Problem Involving a and b
2009-08-24Mathematics10 eqproof limit
- Calculus Study Notes (I): Limits
2009-08-16Mathematics16 eqlearning calculus limit
- The Integral Test for Convergence of Infinite Series
2009-08-12Mathematicsseries summation integral
- The Quest for Mersenne Primes
2009-08-07Mathematicsprime number prime number exploration
- Logical Reasoning: How Many Points Did They Get (PuzzleUp)
2009-08-06Mathematicslogic reasoning
- Two infinite series: the sum of reciprocals of natural numbers and their squares
2009-08-05Mathematics8 eqseries natural number reciprocal square
- A Series Summation Proof (Without Mathematical Induction)
2009-08-02Mathematics4 eqseries summation mathematical induction
- The Perimeter and Area of an Ellipse
2009-08-01Mathematics8 eqellipse perimeter area
- On Proofs Concerning Irrational Numbers and Their Sums
2009-07-31Mathematics8 eqproof summation irrational number
- The Fun Side of Everyday Math: How Likely Is a Shared Birthday?
2009-07-29Mathematicsreprint probability fun
- The Three-Hundred-Year Mystery — Fermat's Last Theorem (History + Proof)
2009-07-28Mathematicsproof mystery theorem history
- A Number Theory Problem About Natural Numbers
2009-07-26Mathematicsnatural number pigeonhole principle
- The "Conspiracy" to Slow Down American Mathematical Progress
2009-07-26Mathematicsmystery united states flash attention black hole number
- Solving Cubic Equations by Radicals (A Popular-Science Version)
2009-07-19Mathematics16 eqequation algebra formula root finding
- Kexue.fm: An Interesting Kind of Square Number
2009-07-08Mathematics6 eqsquare fun number