Welcome to the Artificial Intelligence lecture
The course will cover the basic ideas and techniques underlying the design of intelligent machines. By the end of this course, you will have learned how to build autonomous (software) agents that efficiently make decisions in fully informed, partially observable and adversarial settings as well as how to optimize actions in uncertain sequential decision making environments to maximize expected reward.
- Informed search
- Uninformed search
- Adversarial search
- Constraint Satisfaction Problems
- Local search and Optimization
- Markov Decision Processes
- Reinforcement Learning
- Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (http://aima.cs.berkeley.edu/)
- Richard Sutton and Andrew Barto, Reinforcement Learning: An Introduction (https://mitpress.mit.edu/books/reinforcement-learning-second-edition), for the last part of the course.
Basic knowledge of mathematics, algorithms & data structures and programming (Python).
We will upload videos of lectures and tutorials (links will be announced each time via Whiteboard) and we will offer slots for online, live Q&A sessions (the slots will be within the planned lecture and tutorial slots, to be specified soon).
Lectures: online live Q&As sessions: Wednesdays, 09:00-10:00
- Meeting number: 121 333 2905
- Password: UbvFpGNJ733
Tutorials: online live Q&As sessions: Tuesdays, 16:15-17:15
- Meeting number: 121 807 6671
- Password: 6Ct377mpEvQ
To pass the course
To pass the course, you need to pass i) the exam in the end & you need to pass ii) two projects (formal requirement "Aktive Teilnahme")
Project 1 will be announced on 17/5/2021 and is about implementing uninformed and informed search algorithms. The deadline will be on: 14.06.2021.
Project 2 will be announced on 21/6/2021 and is about implementing adversarial search algorithms. The deadline will be on: 19.07.2021.
- For the projects, you can work in teams of 2 persons.