Courses
14 sections · 75 lessons
6 lessons
Math Foundations
The calculus and linear algebra behind every neural net
Gradient DescentSigmoid & ReLUSoftmax+3 more
6 lessons
Build a Neural Net
Neurons, layers, and backprop — wired by hand
Single NeuronBackpropagationMulti-Layer Backpropagation+3 more
4 lessons
PyTorch
Swap NumPy for autograd and GPUs
PyTorch BasicsLayer NormalizationBatch Normalization+1 more
4 lessons
Training
The loop, the diagnostics, the first real model
Training LoopTraining DiagnosticsDead ReLU Detector+1 more
6 lessons
CNNs & Vision
Filters, feature maps, and the architectures that taught machines to see
Convolution OperationPoolingBuild a CNN from Scratch+3 more
5 lessons
RNN & LSTM
Sequence modeling before attention — and the problems that motivated it
Recurrent Neural NetworkBackprop Through TimeVanishing Gradient Problem+2 more
4 lessons
NLP
From bag-of-words to dense meaning vectors
Word EmbeddingsIntro to Natural Language ProcessingSentiment Analysis+1 more
3 lessons
Attention & Transformers
The single mechanism that reshaped deep learning
Self AttentionMulti Headed Self AttentionTransformer Block
10 lessons
Build GPT
A working GPT, built lesson by lesson
Tokenizer (Byte Pair Encoding)Build VocabularyTokenization Edge Cases+7 more
6 lessons
Fine-Tuning & RLHF
From a base model to an aligned, instruction-following assistant
Supervised Fine-TuningLoRAQLoRA+3 more
4 lessons
Mixture of Experts
Sparse activation — the next axis of scale
MoE FundamentalsTop-k RoutingLoad Balancing Loss+1 more
6 lessons
Diffusion Models
Generate images by learning to reverse noise
Denoising IntuitionForward & Reverse DiffusionU-Net Architecture+3 more
6 lessons
Reinforcement Learning
Learn from reward signals — the algorithms behind AlphaGo and RLHF
Markov Decision ProcessesQ-LearningPolicy Gradients+3 more
5 lessons
Inference & Serving
Ship the model — make it fast, cheap, and production-ready
Quantization BasicsINT8 & INT4 QuantizationSpeculative Decoding+2 more