Modern and durable foundations for machine learning, deep learning, probability, and the math underneath contemporary AI systems.
“A practical modern baseline for moving from Python to real ML and deep-learning workflows.”
“A newer deep-learning text that covers modern topics such as transformers and diffusion while staying readable.”
“A rigorous but current probabilistic view of ML, useful for readers who need more than cookbook fluency.”
“A compact math foundation covering linear algebra, calculus, optimization, probability, and statistics for ML.”
“A Keras 3-era deep learning text for readers who want practical neural-network work tied to modern generative AI workflows.”
“Also belongs here because implementing a small LLM is one of the clearest ways to understand modern model internals.”