PHY 4905 "Machine Learning"
(Spring 2021)
Main books (required)
- Jake VanderPlas, Python Data Science Handbook (free).
- F. Chollet, Deep Learning with Python (new edition in Summer 2021) (code).
- A. Geron, Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (code).
- P. Bruce, A. Bruce and P. Gedeck, Practical Statistics for Data Scientists (code).
- D. Foster, Generative Deep Learning (blog post and code).
- A. Trask, Grokking Deep Learning (code).
- P. Wilmott, Machine Learning: An Applied Mathematics Introduction.
- Recently Springer released a number of Machine Learning and Data books for free.
- T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning (free).
- M. Nielsen, Neural Networks and Deep Learning (free online book).
- I. Goodfellow, Y. Bengio and A. Courville, Deep Learning (free).
- J. Patterson and A. Gibson, Deep learning: A Practitioner's Approach (very inexpensive).
Python resources
- Jake VanderPlas, A whirlwind tour of python.
- The python tutorial at python.org.
Free online resources
- Machine Learning course at Stanford
- Introduction to Deep Learning course at MIT.
- The AI roadmap from a blog post by a former physicist.
Some relevant arXiv articles
- Mehta et al., Introduction to Machine Learning for physicists
- Jared Kaplan's notes on Contemporary Machine Learning for Physicists
- Carleo et al., Machine learning and the physical sciences
- D. Bourilkov, Machine and Deep Learning Applications in Particle Physics
- K. Albertsson et al., Machine Learning in High Energy Physics Community White Paper
Return to the PHY 4905 Machine Learning home page