Book I
ML foundations
Math, probability, classical machine learning, deep learning, and the core questions that test them.
9 chapters · 62 entriesChapters
9Linear algebra and geometry
Start with linear maps, then study volume, spectra, decompositions, and derivatives.
Probability and statistics
Build from moments and distributions to estimation, uncertainty, testing, and resampling.
Supervised learning
Move from linear models to kernels, trees, and ensembles.
Unsupervised learning
Clustering and low-dimensional views of unlabeled data.
Neural network foundations
Understand expressiveness, optimization by backpropagation, and stable deep networks.
Representations and architectures
Connect attention, encoders, self-supervision, graphs, and generative structure.
Probabilistic and latent-variable models
Build latent-variable and structured models before modern deep generative models.
Deep generative models
Study autoencoders, flows, adversarial learning, and diffusion in a useful sequence.
Foundation interview questions
Test mechanism, assumptions, trade-offs, and changed conditions.