Instructor
Dr. Charley Wu (charley[dot]wu[at]uni-tuebingen[dot]de)
Teaching Assistants
Hanqi Zhou (hanqi[dot]zhou[at]uni-tuebingen[dot]de)
Turan Orujlu (turan[dot]orujlu[at]uni-tuebingen[dot]de)
Alexandra Witt (Alexandra[dot]Witt[at]gmx[dot]net)
General Information
Lecture: Tuesdays @ 12:00 - 14:00 Seminar Room 4332, Psychology Faculty (Alte Frauenklinik), Schleichstraße 4, 72076 Tübingen
Tutorial: Wednesdays @ 16:00-18:00 3rd Floor Meeting Room, AI building, Maria-von-Linden-Str. 6, D-72076 Tübingen
Office Hours: By appointment
Course description and prerequisites:
The goal of the course is to teach modern approaches to machine learning in parallel with the science of human learning. Theories of human learning have directly inspired algorithms for training artificial agents, while advances in AI have provided novel insights into the nature of human intelligence. Machine learning algorithms are increasingly reaching or exceeding human-level expertise. Yet, they can still be fooled by rather trivial tasks that any human could solve. How have these two fields separately approached the study of artificial and biological intelligence? What are general principles of learning that are shared across human and machine learners?
The course covers how both biological and artificial systems i) learn from experience (Reinforcement Learning), ii) learn about concepts and categories, and ii) learn functions and programs. Each week, there will be one lecture and one tutorial session. No prerequisites are required, but some basic familiarity with linear algebra and basic mathematical notation will be necessary.
Grading
Schedule
Note that readings are still subject to change
| Date | Remarks | Lecture | Tutorial | TA | Readings |
|---|---|---|---|---|---|
| Week 1: | Oct 15: Introduction (slides) | Oct 16 (slides) | Alex | Spicer & Sanborn (2019). What does the mind learn? | |
| Week 2: | Oct 22: Origins of biological and artificial learning (slides) | Oct 23 (slides) | Turan | [1] Behaviorism [2] What is a perceptron? (Blog post) | |
| Week 3: | Oct 29: Symbolic AI and Cognitive maps (slides) | Oct 30 (Quiz #1) | Alex | [1] Garnelo & Shanahan (2019) [2] Boorman et al., 2021 | |
| Week 4: | Nov 5: Introduction to RL (slides) | Nov 6 (slides) | Turan | Sutton & Barton (Ch. 1 & 2) | |
| Week 5: | Nov 12: Advances in RL (slides) | Nov 13 (Quiz #2) | Turan | Neftci & Averbeck (2019) | |
| Week 6: | Guest lecturer: Alexandra Witt | Nov 19: Social learning (slides) | Nov 20 (slides) | Alex | Witt et al., (2024) |
| Week 7: | Guest lecturer: Dr. David Nagy | Nov 26: Compression and resource constraints (slides) | Nov 27 (slides) | David | Nagy et al., (2020) |
| Week 8: | Dec 3: Concepts and Categories (slides) | Dec 4 (Quiz #3) | Hanqi | Murphy (2023) | |
| Week 9: | Dec 10: Supervised and Unsupervised learning (slides) | Dec 11 | Hanqi | Bishop (Ch. 4) | |
| Holiday break | |||||
| Week 10: | Jan 14: Function learning | Jan 15 | Alex | Wu, Meder, & Schulz (in press) | |
| Week 11: | Jan 21: No Lecture | Jan 22: No Tutorial | |||
| Week 12: | Jan 28: Language and semantics | Jan 29 | Hanqi | Kamath et al., (2024) | |
| Week 13: | Feb 4: General Principles | Feb 5 | Charley | Gershman (2023) | |
| Exam 1 | 13:00-15:00 21.02.2025 Hörsaal 1 F119 (SAND) | ||||
| Exam 2 | 12:00-14:00 11.04.2025 Ground floor lecture room, AI building, Maria-von-Linden-Str. 6, D-72076 Tübingen |