Pytorch

PyTorch Transforms: From Raw Data to the Tensor Your Model Actually Sees
Models From First Principles 08: Preference Rankers — Learning Which Answer Is Better
Cellular Automata From First Principles 51: Run Cellular Automata on the GPU
Cellular Automata From First Principles 48: What Did the Neural CA Actually Learn?
Cellular Automata From First Principles 47: Inspect Hidden-State Propagation
Cellular Automata From First Principles 43: Test Generalization Beyond Training
Cellular Automata From First Principles 46: Generalize to Harder and Larger Mazes
Cellular Automata From First Principles 42: Regenerate After Damage
Cellular Automata From First Principles 45: Learn to Solve Mazes
Cellular Automata From First Principles 41: Train for Persistence
Cellular Automata From First Principles 44: Neural Cellular Automata for Pathfinding
Cellular Automata From First Principles 40: Randomize the Update Schedule
Cellular Automata From First Principles 39: Grow a Target From One Seed
Cellular Automata From First Principles 38: Hidden Cell Channels and Local Memory
Cellular Automata From First Principles 37: Learn the Local Update Rule
Cellular Automata From First Principles 36: Make the Automaton Differentiable
Models From First Principles 08: Which Model Should You Use? MR.Q, EBT, SICQL, HRM, Tiny and PACS Compared
Models From First Principles 07: PACS — Building an Optimizer From Gradient Statistics
Models From First Principles 06: Inside Tiny — Residual Blocks, Attention and Sparse Autoencoders
Models From First Principles 05: Tiny — Recursive Reasoning With a Small Neural Network
Models From First Principles 04: HRM — Hierarchical Reasoning With Fast and Slow Recurrent State
Models From First Principles 03: SICQL — Building a Model From Q, V and Policy Networks
Models From First Principles 02: EBT — From One Score to Q, V, Policy and Advantage
Models From First Principles 01: MR.Q — Building a Neural Quality Model From Two Embeddings
Models From First Principles 00: The Model Inside the Model
10: Build a Small GPT-Style Language Model From Scratch
Training Regressions and Reproducible Experiments: When Nothing Crashes but the Model Gets Worse
PyTorch Compiler Debugging: Graph Breaks, Guards, Recompiles and torch.compile
PyTorch Performance Debugging: CUDA OOM, Slow Training, GPU Utilization and torch.compile
PyTorch Model Not Learning? A Systematic Debugging Guide
PyTorch Attention Shapes: Q, K, V, Multi-Head Attention Masks and Transformer Dimension Errors
Beyond 3D: Tensors, 100 Dimensions and an SVM From Scratch
PyTorch CNN Shape Errors: Conv2d Output Sizes, Channels, Flatten Bugs and How to Debug Them
PyTorch DataLoader Performance: num_workers, pin_memory, Prefetching and Why Your GPU Is Waiting
The Most Important Idea in PyTorch: Recursive Composition
Build a Neural Network From Scratch in PyTorch Without nn.Module
PyTorch Autograd Debugging: requires_grad, detach, backward() and NaN Gradients
PyTorch Tensor Shapes: Broadcasting, Reshape, View, Permute and the Errors That Waste Your Time
00: What Are We Actually Doing?
MR.Q: Model-Based Representations for Model-Free Trading
Writing Neural Networks with PyTorch