CMPU 319 - Modeling Minds, Brains, and Behavior

Semester Offered: Fall
1 unit(s)

(Same as COGS 319) This course explores computational models as a powerful tool for developing and testing scientific theories in cognitive science. What exactly are models? How can models be used to test hypotheses? How do we decide whether one model is better than another? Why is modeling such an important part of the scientific process? We will tackle these sorts of questions through hands-on creation and exploration of models, as well as discussion of research papers that exemplify modeling work in cognitive science. By the end of the course, students will understand the foundational issues of modeling, be better consumers of research that uses modeling, and be able to build their own models. Because there are a wide variety of modeling approaches used in cognitive science, the focus of this class changes periodically to cover different areas of modeling. The course may be repeated for credit if the topic has changed.

Topic for 2024/2025a: Neural networks and deep learning. Neural networks have been instrumental in understanding cognition and driving advancements in AI. This course explores their journey, from the earliest models in cognitive science to cutting-edge deep learning models powering systems like ChatGPT, Midjourney, and AlphaZero. Students will learn how to build and train neural networks in Python using the TensorFlow ecosystem. Prior programming experience in python is not required, but students without such experience should consult with the instructor before enrolling. Joshua de Leeuw.

Prerequisite(s): A 200-level course in Cognitive Science, Computer Science, or a related discipline; or permission of the instructor.

One 2-hour period plus one 50-minute period.

Course Format: CLS