|
Highly recommended but not strictly required textbooks
Used copies of the books below should be easily found on Amazon.
Machine Learning: M1
by Tom Mitchell (1997) ... Yes, it is "old" but it gives a lot of intuition for the key ideas in machine learning that are important today, and is somewhat less heavy on the math.
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems M2
2nd Edition (2019) by Aurelien Geron
Deep Learning with Python: D
2nd Edition (2021) by Francois Chollet
Other good textbooks (available free online!)
Deep Learning
by Ian Goodfellow, Yoshua Bengio, Aaron Courville (2016)
Neural Networks and Deep Learning
Michael A. Nielsen, (2015)
A Course in Machine Learning: M2
by Hal Daumé III (2017)
Machine Learning: An Applied Mathematics Introduction
by Paul Wilmott (2020)
Probabilistic Machine Learning: An Introduction
by Kevin Patrick Murphy (2022)
Pattern Recognition and Machine Learning
by Christopher M. Bishop (2018)
Information Theory, Inference, and Learning
by David MacKay (2003)
Reinforcement Learning: An Introduction: RL
2nd Edition (2018) by Richard S. Sutton, Andrew G. Barto
Your python3 environment
It is up to you whether you want to run python locally on your own computer or using Google Colab. You can find out more about Google Colab here, including an overview of basic features here .
Python libraries we will use:
Machine Learning Resources
ML reference
ML course (Utah)
ML course (UPenn)
ML course (Alberta)
ML course (IIT Madras)
Deep Learning course (IIT Madras)
Reinforcement Learning course (IIT Madras)
Probability course (UMASS)
Probability course (MIT)
Linear algebra course (MIT)
Linear algebra course (IIT Madras)
Linear algebra review (Stanford)
|
|---|