Part 1 of the ML Lab suite
From matricesto memory.
Rebuild the math, then build the machine. Linear algebra, calculus and neural networks, up to an LSTM you design and train yourself.
Work it on paper
Short derivations and hand calculations, with each step of the worked solution revealed one at a time.
Check your answer
Type a number, vector or matrix and find out right away. Unlimited practice sets generate fresh problems.
Write the code
Real Python and numpy, running in this tab. You implement each piece; tests tell you exactly what is off.
Prove it
Each module ends in a checkpoint. Pass it before moving on, or come back to the parts that slipped.
Part 1. From matrices to memory
Course overview- 00The mapWhere the field is, and how this lab works40 min
- 01Vectors and the dot productLists of numbers that are also arrows85 min
- 02Matrices are machinesA matrix is a function you can write down95 min
- 03Determinants, inverses and rankWhat a transformation does to space65 min
- 04Eigenvectors and eigenvaluesThe directions a matrix does not turn105 min
- 05Derivatives, gradients and JacobiansHow outputs move when inputs move135 min
- 06Neural networks from scratchLayers, losses and backpropagation, by hand155 min
- 07Recurrent networksA network with a memory, unrolled through time115 min
- 08LSTMsMemory with gates225 min
- 09From LSTMs to today's modelsAttention, pretraining, post-training and vision120 min
The whole suite
RoadmapFrom matrices to memory
The math refresher and the first real models: vectors, matrices, eigenvalues, Jacobians, backpropagation, recurrent networks and LSTMs trained in your browser.
Available nowAttention and transformers
Build a small GPT: tokenization, embeddings and positions, self-attention, the transformer block, training, sampling and the KV cache.
PlannedPretraining at scale
What changes when the model and data get large: data pipelines, scaling laws, optimizers and schedules, mixed precision and parallelism.
PlannedPost-training
Turning a base model into an assistant: supervised fine-tuning, reward models, RLHF and DPO, reinforcement learning with verifiable rewards, LoRA and distillation.
PlannedVision
Convolution, CNNs, detection from sliding windows to the R-CNN family, segmentation with FCN, U-Net and Mask R-CNN, vision transformers and CLIP.
PlannedModels in products
Inference, quantization, retrieval, evaluation and agents: the engineering between a trained model and something a customer relies on.
Planned