Machine learning#
These chapters cover the standard methods of machine learning. Classification and evaluation come first: the models that predict labels, then the losses, metrics and cross-validation used to judge them. Unsupervised learning covers clustering, dimensionality reduction and deep generative models; the short kernels chapter connects SVMs to spectral clustering.
Deep learning gives the shared machinery of neural networks, and the computer vision and NLP chapters apply it to images and text, alongside the classical methods that came before. Learning theory closes the part with the question behind all of it: how many examples a learner needs to generalize.
Linear classifiers as regularizer plus loss, SVMs, trees and forests, naive Bayes and Gaussian classifiers, nearest neighbors, and boosting.
Losses and risk, precision, recall and ROC curves, cross-validation, and resampling for stability.
Clustering, dimensionality reduction, deep generative models (VAEs, GANs, diffusion, flows), and self-supervised and contrastive learning.
Valid kernels and their RKHS, and how the eigenvectors of a kernel matrix reveal clusters.
Backpropagation, the main architectures (CNNs, RNNs, GNNs), normalization layers, and training tricks.
How images form, how to filter them and find features, stereo and motion, human vision, and deep networks for vision.
NLP tasks and benchmarks, tokenization, word embeddings, n-gram language models, and parse trees.
How many examples a learner needs, from PAC bounds and VC dimension to version spaces.