Books and on-line resources

Recommended reading. You can use or own resources which, however, may differ in some terminology.

[Russell-Norvig2010] is the main course book. We will not need the whole book. A more detailed recommendation will be provided throughout the course. Note the large on-line content at http://aima.cs.berkeley.edu

Especially when discussing Reinforcement learning and MDPs, we will make use of [Sutton-Barto2018], on-line pdf.

[Bishop2006] is an excellent textbook for machine learning, classifiers, ROC, perceptron … PDF is freely downloadable.

For Python we recommend [Wentworth2012] or [Downey2009]; the newer and Python 3.x fully compatible [Wentworth2012] is probably the better option. Object-Oriented Programming in Python is a good on-line textbook.

You can also use multiple on-line resources:

• Intro to AI course at Berkeley (check also Intro to AI 2018). This course has strongly influenced/motivated our course.
• Artificial Intelligence course at CTU. A master course, now taught with changed content. SDPs and Reinforcement learning

CTU courses for possible specializations. If you fall in love with some parts of our course, you may dig deeper in the following courses:

• Pattern Recognition and Machine Learning a bachelor course at CTU goes deeper into (statistical) machine learning.
• Introduction into Artificial Intelligence a bachelor course at CTU studies deeper games and knowledge representation.
• Statistical Machine Learning a master course at CTU goes deep into the theory of statistical machine learning. (Notably: SVM, EM algorithm, Neural Networks, Reinforcement Learning).

You may also consider participating in research projects as a summer intern or doing an individual project or accomplishing a bachelor/master thesis.

• https://sites.google.com/site/matejhof/student-projects/open-and-ongoing
• http://cyber.felk.cvut.cz/people/svobodat/
• http://robotics.fel.cvut.cz/

For your own curiosity, if you'd like to go deeper on the topic of Adversarial Search, here's some repositories related to the code of AlphaGo and AlphaZero (Go and Chess AIs), with Monte Carlo Tree Search (MCTS) implementations:

• https://github.com/deepmind/mctx
• https://github.com/leela-zero/leela-zero

Again for your own curiosity, if you'd like to know how ChatGPT and other “Large Language Models” work, this is a very long but good post, that also makes some links with the Recognition Tasks, and Classifiers parts of the course:

• https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/