└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Mathematics for Machine Learning 2 | 3 | A collection of resources to learn mathematics for machine learning. 4 | 5 | ## Mathematics for Machine Learning 6 | *by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong* 7 | 8 | This is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it. 9 | 10 | Book: https://mml-book.github.io 11 | 12 | ## The Elements of Statistical Learning 13 | *by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie* 14 | 15 | Machine learning deals with data and in turn uncertainty which is what statistics aims to teach. Get comfortable with topics like estimators, statistical significance, etc. 16 | 17 | Book: https://hastie.su.domains/ElemStatLearn/ 18 | 19 | If you are interested in an introduction to statistical learning, then you might want to check out ["An Introduction to Statistical Learning"](https://www.statlearning.com/) 20 | 21 | ## Probability Theory: The Logic of Science 22 | *by E. T. Jaynes* 23 | 24 | In machine learning, we are interested in building probabilistic models and thus you will come across concepts from probability theory like conditional probability and different probability distributions. 25 | 26 | Source: https://bayes.wustl.edu/etj/prob/book.pdf 27 | 28 | ## Probabilistic Machine Learning: An Introduction 29 | *by Kevin Patrick Murphy* 30 | 31 | This book contains a comprehensive overview of classical machine learning methods and the principles explaining them. 32 | 33 | Book: https://probml.github.io/pml-book/book1.html 34 | 35 | ## Multivariate Calculus by Imperial College London 36 | *by Dr. Sam Cooper & Dr. David Dye* 37 | 38 | Backpropagation is a key algorithm for training deep neural nets that rely on Calculus. Get familiar with concepts like chain rule, Jacobian, gradient descent,. 39 | 40 | Video Playlist: https://www.youtube.com/playlist?list=PLiiljHvN6z193BBzS0Ln8NnqQmzimTW23 41 | 42 | ## Mathematics for Machine Learning - Linear Algebra 43 | *by Dr. Sam Cooper & Dr. David Dye* 44 | 45 | Agreat companion to the previous video lectures. Neural networks perform transformations on data and you need linear algebra to get better intuitions of how that is done. 46 | 47 | Video Playlist: https://www.youtube.com/playlist?list=PLiiljHvN6z1_o1ztXTKWPrShrMrBLo5P3 48 | 49 | ## Mathematics for Deep Learning 50 | 51 | This reference contains some mathematical concepts to help build a better understanding of deep learning. 52 | 53 | Chapter: https://d2l.ai/chapter_appendix-mathematics-for-deep-learning/index.html 54 | 55 | ## The Matrix Calculus You Need For Deep Learning 56 | *by Terence Parr & Jeremy Howard* 57 | 58 | In deep learning, you need to understand a bunch of fundamental matrix operations. If you want to dive deep into the math of matrix calculus this is your guide. 59 | 60 | Paper: https://arxiv.org/abs/1802.01528 61 | 62 | ## Information Theory, Inference and Learning Algorithms 63 | *by David J. C. MacKay* 64 | 65 | When you are applying machine learning you are dealing with information processing which in essence relies on ideas from information theory such as entropy and KL Divergence,... 66 | 67 | Book: https://www.inference.org.uk/itprnn/book.html 68 | 69 | ## Foundations of Machine Learning 70 | *by Mehryar Mohri, Afshin Rostamizadeh & Ameet Talwalkar* 71 | 72 | A comprehensive and accessible overview of the mathematics behind most learning algorithms (except deep learning). The appendix alone is worth a detour. 73 | 74 | Book: https://cs.nyu.edu/~mohri/mlbook/ 75 | 76 | --- 77 | This collection is far from exhaustive but it should provide a good foundation to start learning some of the mathematical concepts used in machine learning. Reach out on [Twitter](https://twitter.com/omarsar0) if you have any questions. 78 | --------------------------------------------------------------------------------