d2l::interactive

d2l.ai // rebuilt as an interactive lab

Deep learning you can scroll, drag, and break.

Every chapter of Dive into Deep Learning as a visual story: algorithms running live in your browser, figures that advance as you scroll, and labs where you turn the dials yourself.

Applications

14

Computer Vision

Augmentation, fine-tuning, object detection, segmentation, and neural style transfer.

○ planned
15

NLP: Pretraining

word2vec, GloVe, subword embeddings, and BERT — words as vectors you can do arithmetic on.

○ planned
16

NLP: Applications

Sentiment analysis and natural language inference with RNNs, CNNs, and fine-tuned BERT.

○ backlog
21

Recommender Systems

Matrix factorization to deep factorization machines on real ratings data.

○ backlog

Frontiers

17

Reinforcement Learning

Markov decision processes, value iteration sweeping a gridworld, and Q-learning.

○ planned
18

Gaussian Processes

Priors over functions: uncertainty you can see.

○ backlog
19

Hyperparameter Optimization

Random search, successive halving, and asynchronous scheduling.

○ backlog
20

Generative Adversarial Networks

A generator and a discriminator locked in a duel — watch fake data sharpen into the real thing.

○ planned

Bonus

0A

Math for Deep Learning

Geometry of linear algebra, eigendecompositions, calculus, probability distributions, and information theory.

○ backlog