For now, this is a reading list, designed for my students.
- The stanford class https://cs231n.github.io/ is excellent !
- The NYU Center for Data Science class https://www.youtube.com/watch?v=0bMe_vCZo30&list=PLLHTzKZzVU9eaEyErdV26ikyolxOsz6mq and possibly the notes related to the course: https://atcold.github.io/pytorch-Deep-Learning/
- The main reference (general Machine Learning): Pattern Recognition and Machine Learning, Christopher Bishop, 2006 (easily found – you don’t even need sci-hub for this one !)
- More of an information-theoretic perspective: Information Theory, Inference, and Learning Algorithms, David J.C. MacKay (same remark, just google it)
- https://scikit-learn.org/stable/user_guide.html this is more than a simple documentation for using packages. These help pages always start with a documented description of the algorithms implemented in each class’ function. Links to the original papers are provided. And when you click down from classes to nested classes to functions, you find a usual documentation with arguments lists, etc.
- Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Aurélien Géron https://github.com/yanshengjia/ml-road/blob/master/resources/
- Machine Learning avec Scikit-Learn – 2e éd. – Mise en oeuvre et cas concrets, Aurélien Géron
Suggestions by the distinguished Guillaume Charpiat (I think he has good taste):
Suggestions by Isabelle Guyon:
[TOTAL BEGINNER COURSE] Introduction to machine learning, Sebastian Thrun, Katie Malone, Udacity (10 lessons)
[BEGINNER COURSE] Machine Learning, Andrew Ng, Coursera (54 hours)
[BOOK] The Hundred-Page Machine Learning Book. Andriy Burkov.
[BOOK] Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. Aurélien Géron.
[ADVANCED COURSE] How to win a data science competition. Dmitry Ulianov, Coursera, (4 weeks); Excellent summer program!