|
1.1 Neural Networks: A Learnable Function
|
jshn9515
|
2026-04-23
|
|
1.3 Forward Propagation, Backpropagation, and Computation Graph
|
jshn9515
|
2026-03-19
|
|
2.1 Automatic Differentiation in PyTorch: From Forward Computation to Backpropagation
|
jshn9515
|
2026-03-19
|
|
2.2 Gradient Modes in PyTorch: Controlling How Computation Graphs Are Recorded
|
jshn9515
|
2026-03-19
|
|
2.3 Data Loading in PyTorch: Dataset, DataLoader, and Batching
|
jshn9515
|
2026-05-23
|
|
2.4 nn.Module in PyTorch: Organizing Models, Parameters, and State
|
jshn9515
|
2026-05-23
|
|
2.5 Optimizers in PyTorch: From Manual Updates to Parameter Groups and State Management
|
jshn9515
|
2026-05-23
|
|
2.6 Training Loop in PyTorch: Connecting Data, Models, and Optimizers
|
jshn9515
|
2026-05-23
|
|
2.7 Checkpoints in PyTorch: Resuming Training After Interruption
|
jshn9515
|
2026-05-28
|
|
3.1 From Linear Classifiers to MLPs: Why We Need Hidden Layers
|
jshn9515
|
2026-06-07
|
|
3.2 Activation Functions: Adding Nonlinearity to Neural Networks
|
jshn9515
|
2026-06-07
|
|
3.3 Softmax and Cross Entropy: From Logits to Classification Loss
|
jshn9515
|
2026-06-07
|
|
3.4 Forward and Backward Propagation of Linear Layers
|
jshn9515
|
2026-06-07
|
|
3.5 Building a Complete MLP with NumPy
|
jshn9515
|
2026-06-07
|
|
3.6 Train MLP on MNIST with NumPy
|
jshn9515
|
2026-06-07
|
|
3.7 Backward Propagation Check: Using Numerical Gradients to Verify Handwritten Backward
|
jshn9515
|
2026-06-07
|
|
3.8 Reimplementing MLP with PyTorch nn.Module
|
jshn9515
|
2026-06-07
|
|
4.1 From Gradient Descent to SGD
|
jshn9515
|
2026-05-29
|
|
4.2 Momentum and Nesterov Momentum
|
jshn9515
|
2026-05-29
|
|
4.3 Adagrad: Starting Point of Adaptive Learning Rates
|
jshn9515
|
2026-05-29
|
|
4.4 RMSprop and Adadelta: Fixing Learning Rate Decay
|
jshn9515
|
2026-05-29
|
|
4.5 Adam: Combining Momentum and RMSprop
|
jshn9515
|
2026-05-29
|
|
4.6 AdamW: Decoupled Weight Decay
|
jshn9515
|
2026-05-29
|
|
4.7 Muon: Orthogonalized Updates for Matrix Parameters
|
jshn9515
|
2026-06-05
|
|
4.8 Optimizer Map: When to Use Which Optimization Algorithm
|
jshn9515
|
2026-06-05
|
|
4.9 Learning Rate Schedulers: Letting the Learning Rate Change During Training
|
jshn9515
|
2026-06-05
|