~/ml

Study notes from the ground up — the math behind ML, deep learning theory, classic architectures, and papers re-implemented from scratch.

2024

10-10 GPT-1 #papers
10-03 Transformer #papers
09-23 Evaluation in NLP #transformer
09-20 Transformer #transformer
09-12 Tokenizing #transformer
09-10 Self Attention #transformer
09-06 Seq2Seq #transformer
09-04 RNN and Attention #transformer
09-01 RNN and its cons #transformer
09-01 RNN and its pros #transformer
08-15 EfficientNet #papers
08-11 MobileNet V3 #papers
08-07 MobileNet V2 #papers
08-03 SENet #papers
07-30 MobileNet V1 #papers
07-26 ResNeXt #papers
07-24 DenseNet #papers
07-20 WideResNet #papers
07-18 Pre-Act. ResNet #papers
07-15 Inception V2/V3 #papers
07-12 ResNet #papers
07-10 Inception V1 #papers
07-07 VGGNet #papers
07-03 R-CNN #papers
05-27 mAP #object_detection
05-26 Soft-NMS #object_detection
05-25 IoU & NMS #object_detection
05-24 Selective Search #object_detection
05-22 Sliding Window #object_detection
05-21 Concepts of Object Detection #object_detection
05-16 Attention #dl_theory
05-15 Seq2Seq #dl_theory
05-14 RNN Back Propagation #dl_theory
05-14 RNN #dl_theory
05-13 CNN Summary #dl_theory
05-12 VGGNet #dl_theory
05-11 CNN Feature Map #dl_theory
05-10 Padding, Pooling, Striding #dl_theory
05-09 CNN with 3D input #dl_theory
05-09 CNN Feature Extraction #dl_theory
05-08 CNN #dl_theory
05-07 Regularization #dl_theory
05-06 Dropout #dl_theory
05-06 Overfitting & Data Augmentation #dl_theory
05-05 Loss Landscape / Skip-Connection #dl_theory
05-03 Batch Normalization #dl_theory
05-02 Vanishing Gradient #dl_theory
05-02 ReLU #dl_theory
05-01 Universal Approximation Theorem #dl_theory
04-30 Multi-class Classification #dl_theory
04-29 Neural Network is MLE machine #dl_theory
04-28 MSE vs. Likelihood #dl_theory
04-27 Perceptron #dl_theory
04-27 Binary Classification (Sigmoid) #dl_theory
04-26 Back Propagation with Matrix Derivatives #dl_theory
04-25 Back Propagation #dl_theory
04-24 MLP & Non-Linearity #dl_theory
04-23 K-fold Cross Validation #dl_theory
04-23 Train, Valid, Test #dl_theory
04-22 Adam #dl_theory
04-22 Momentum vs. RMSProp #dl_theory
04-21 Mini-Batch SGD #dl_theory
04-21 Stochastic Gradient Descent #dl_theory
04-20 Weight Initialization #dl_theory
04-20 Gradient Descent #dl_theory
04-19 Linear Regression #dl_theory
04-19 Neural Network #dl_theory
04-13 Information Theory #math
04-12 Maximum A Posteriori #math
04-12 Maximum Likelihood Estimation #math
04-11 Uniform and Normal Distribution #math
04-11 Mean and Variance #math
04-11 Random Variable and Probability Distribution #math
04-10 Vector derivative respect to Matrix #math
04-10 Matrix derivative respect to Matrix #math
04-09 Scalar derivative respect to Matrix #math
04-08 Vector derivative respect to vector (Chain Rule) #math
04-08 Vector derivative respect to vector #math
04-07 Gradients #math
04-06 Scalar derivative respect to vector #math
04-05 MacClaurin & Taylor Expansion #math
04-04 Partial Derivative #math
04-04 Chain Rule #math
04-04 Derivative #math
04-03 Limits #math
04-02 Transpose & Dot Product #math
04-02 Vector & Matrix #math
04-01 Logarithmic Function #math
04-01 Function #math