| Literature |
Machine Learning textbooks:
- Stephen Marsland, Machine Learning, An Algorithmic Perspective,
2nd Ed., Chapman & Hall, 2014.
(We have several copies in the department library, you might also find free download links.)
- Trevor Hastie, Robert Tibshirani, Jerome Friedman,
The Elements of Statistical Learning, Springer 2017.
Free download from the authors' page:
PDF.
- Aurélien Géron,
Hands-On Machine Learning with Scikit-Learn and TensorFlow:
Concepts, Tools, and Techniques for Building Intelligent Systems,
O'Reilly, 2017.
- additional literature will be discussed in the lecture.
For the part on deep learning,
you might want to take a look at these books and tutorials:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville,
Deep Learning, MIT Press, 2017.
- Francois Chollet, Deep Learning with Python,
Manning 2017.
- Yann LeCun, Marc A. Ranzato,
Deep Learning Tutorial, ICML, Atlanta, 2013.
- Geoff Hinton, Yoshua Bengio, Yann LeCun,
Deep Learning, Tutorial, NIPS, 2015.
Reinformcement Learning:
- Sutton and Barto: Reinforcement Learning (Draft of 2nd. Ed., 2013)
book homepage.
-
Another recent book is
Reinforcement Learning:
State-of-the-Art by M. Wiering and M. van Otterlo (editors), 2012.
It first discusses the basic notation and algorithms, and then provides
advanced materials by many of the leading RL experts.
An electronic version is available via SpringerLink (campus access).
-
Visit the 2017
Deep RL Bootcamp
for presentations (slides and videos) of the leading RL researchers.
Covers all topics from RL basics to cutting-edge approaches.
|
