CS 274A: Textbook References

Primary Reference Text for CS 274A

• Mathematics for Machine Learning, by Diesenroth, Faisal, and Ong, Cambridge University Press, 2020 (PDF freely available online). A very useful reference for many of the mathematical concepts we will cover. Chapters 6, 8, 9, 11 are particularly relevant for this course.

Secondary Reference Texts for CS 274A

• Deep Learning: Foundations and Concepts, by Chris Bishop and Hugh Bishop, Springer, 2023 (freely available online). Although this text is focused on Deep Learning, chapters 1 through 5 serve as useful reference material for this course
• Probabilistic Machine Learning: An Introduction, by Kevin Murphy, MIT Press, 2022 (PDF freely available online). An in-depth reference text for research in probabilistic machine learning, more research-oriented than the two above. It covers far more material than we will be able to cover in this 10-week class. Useful for providing additional reading for what we cover in this class. Chapter 1-6, 9-12, and 21 are of most direct relevance to this class.

Introductory Texts on Probability

• Grinstead and Snell's Introduction to Probability, a well-known reference text on probability.
• Blitzstein and Hwang's Introduction to Probability, a more introductory text, Harvard Statistics, 2019
• Berstekas and Tsitlis's MIT Lecture Notes Introduction to Probability
  (a common theme here in terms of the titles of these books!)

Additional Background Reading on Probabilistic Machine Learning

• Elements of Statistical Learning (2nd ed), 2009, by Hastie, Tibshirani, and Friedman. One of the classic texts in the field of machine learning, emphasizing statistical foundations.
• Probabilistic machine learning and artificial intelligence, Zoubin Ghahramani, Nature, 2015. Good overview article of the role of probability in modern machine learning and AI.
• Model-based machine learning, Chris Bishop, Phil Trans R. Soc. A, 2012. A well-written overview article that reviews some of the key ideas behind probabilistic model-based learning
• Bayesian Reasoning and Machine Learning, by David Barber, Cambridge University Press. A useful reference text on probabilistic learning.

Further Afield ....

• Patterns, Predictions, and Actions: A Story about Machine Learning, 2021, by Hardt and Recht. Recent text on modern machine learning, providing excellent insights.
• Model-Based Machine Learning by John Winn + colleagues, published online, 2023. An interesting applications-oriented perspective on how to use probabilistic machine learning for a variety of real-world machine learning problems.
• Understanding Deep Learning by Simon Prince, MIT Press, 2023; a good modern reference on deep learning.
• Computer Age Statistical Inference, by Efron and Hastie, 2016. An excellent source of information on modern statistical thinking about data analysis, including statistical perspectives on machine learning.