Stanford's foundational deep learning course materials covering linear classifiers, optimization, backpropagation computational graphs, neural network training dynamics, and representation learning.
Originally co-created by Fei-Fei Li and Andrej Karpathy, Stanford CS231n features some of the clearest written course notes and coding assignments ever created on backpropagation, computational graphs, weight initialization, batch normalization, and training diagnostics. Note: While current-quarter Stanford enrollment lectures are restricted to Stanford students, the comprehensive written course notes (`cs231n.github.io`), syllabus, slides, and archived lecture series are publicly accessible.
Course status is tracked independently from roadmap topic checkboxes so you can mark external courses without altering your topic mastery percentage.
Phase 3 Deep-Dive Written Notes & Assignments (Modules 3.1–3.3)
Publicly accessible materials include the official written course notes, lecture slides, syllabus, and assignments. Current-semester live Stanford classroom recordings are restricted to enrolled students, though archived lecture playlists are publicly available.
Status: Verified (2026-11-09)
Review these foundations before starting so you get the most out of this material:
In Phase 3: Deep Learning & Neural Networks
Read the publicly accessible CS231n written notes on Optimization, Backpropagation Intuition, and Neural Networks Part 1–3 (Activations, Initialization, Babysitting the Learning Process).
Neurons, feedforward layers, modern activations (ReLU, GELU, SiLU), forward/backward passes, initialization, normalization, and residual streams.
Building a dynamic reverse-mode autodiff engine (micrograd-style) with computational graphs, topological sorting, and gradient accumulation.
PyTorch tensors, GPU acceleration, autograd mechanics, nn.Module architecture, DataLoaders, checkpointing, and mixed precision.
A code-first introduction to neural networks covering automatic differentiation, backpropagation, language models, and GPT implementations.
Stanford's flagship graduate NLP curriculum covering word vectors (Word2Vec), neural language models, recurrent networks (RNN/LSTM), attention mechanisms, and pretrained Transformers.
Free interactive textbook combining mathematical explanations, code, and practical deep-learning concepts.