Lecture 01
Where Deep Learning Losses Come From I
Distributions, likelihood, and loss.
Lecture library
Notes, slides, practice and videos for every lecture.
Notes Slides Cheat sheet Notebook Recording 3-min summary
Foundations
Lectures 1–4Lecture 02
Where Deep Learning Losses Come From II
MLE, regression, and classification.
3-minute summaries
Lecture 03
Likelihood to Loss in Practice
MAP, regularization, and robust observation models.
Practice notebooks
Lecture 04
From Linear Models to Neural Networks
Neurons, activations, multilayer networks, XOR, and approximation.
Practice notebooks
Gradients and optimization
Lectures 5–9Lecture 05
Optimization I — Gradient Estimates & Step Sizes
Batches, stochastic gradients, and optimizer geometry.
Full recording
Lecture 06
Backpropagation & Autograd from Scratch
Computation graphs, reverse mode, and a scalar engine.
Practice notebooks
Full recording
Lecture 07
Optimization II — Momentum, RMSProp & Adam
Moving averages and adaptive coordinate scaling.
Lecture 08
Vector, Matrix & Affine Autograd
Gradients, Jacobians, dense layers, and batched VJPs.
Practice notebooks
3-minute summaries
Lecture 09
Valid Outputs by Design & Learning-Rate Schedules
Constrained parameters, warmup, decay, and cosine.
Generalization
Lectures 10Lecture 10
Generalization & Regularization
Learning curves, weight decay, early stopping, dropout, augmentation, Mixup, and label smoothing.
Practice notebooks
Attention and language
Lectures 11–15Lecture 11
From characters to next-token prediction
Tokenization, learned embeddings, a hidden-layer MLP, training, and generation.
3-minute summaries
Lecture 12
Self-attention, from first principles
Full recording
3-minute summaries
Lecture 13
Self-attention, continued
Embedding updates, next-token prediction, and positional encoding.
3-minute summaries
Lecture 14
Self-attention and multi-head attention
Lecture 15
From Attention to Applications
Encoder, decoder-only and encoder–decoder Transformers; token and sentence classification; causal self-attention and cross-attention.
Vision and language
Lectures 16–20Lecture 16
Vision Transformer for image classification
Patch embeddings, full attention, embedding updates and CLS readout; CNN comparisons and image-covering experiments. 55 slides including the cover.
Lecture 17
CLIP: From Fixed Labels to Language-Defined Vision
Applications, two encoders, a step-by-step contrastive-loss calculation, zero-shot classification and linear probing.
Lecture 18
From CLIP to Vision-Language Models
Visual prefixes, cross-attention and learned summaries; architecture diagrams, code walkthroughs, training and generation.
Lecture 19
Object Detection: From One Label to a Set of Objects
Spatial candidates, target assignment, worked losses, decoding, NMS, evaluation and DETR-style set prediction.
Interactive practice
Lecture 20
Beyond Boxes: Dense, Structured, and Promptable Vision
Semantic, instance and panoptic segmentation; keypoints, depth, promptable masks and language grounding.
Interactive practice
No lectures match. Try another topic or resource type.
Notes are the complete PDF handouts or interactive lectures. Slides open the classroom presentation. Cheat sheets are two-page reviews.