Useful Books for Machine Learning

Last Updated: Nov 10th, 2023

This is a list of books I’ve read, currently reading, or plan to read which I think are useful for self-studying modern Machine Learning concepts. This page both serves as a reminder for myself that learning should be a continuing progress and a (hopefully helpful) resource for those who want to take their initial step to learn machine learning on their own.

ML Reading List

Overview of ML & Practical Usages

  1. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition (1st Time Finished; Must Read for beginners)

  2. Introduction to Machine Learning with Python: A Guide For Data Scientists (1st Time Finished)

  3. Dive into Deep Learning (Focus almost solely on deep learning and STOA NN architectures; Reading Selectively)

Machine Learning Math

  1. Mathematics for Machine Learning (Currently Reading, 40% Finished)

  2. Understanding Machine Learning: From Theorem to Algorithms

  3. Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning (Too long to be finished; Use more like a tool book; Read Selectively)

  4. The Elements of Statistical Learning (ESL)(Next on the priority list; Focus more on Statistics Concepts)

  5. Introduction to Linear Algebra (Gilbert Strang) (Read for more linear algebra content)

  6. First-Order Methods in Optimization (Read for more Gradient-based Optimizations)