Cutting edge Seminar
Speaker: Hiroshi Makino (Professor, Department of Physiology, Keio University School of Medicine）
Title: Learning in intelligent systems
Date&Time: 28 January(wed) 12：00-13：00
Venue: Conference Room(1F), IMEG, Kumamoto University
※This seminar can also be attended through ZOOM. Please check the URL on “S-HIGO Cutting-Edge Seminar A, B” at Moodle.
https://md.kumamoto-u.ac.jp/course/view.php?id=120331
Abstract:
Recent years have seen a resurgence of interplay between artificial intelligence (AI) and neuroscience. While AI offers new theories on how the brain solves complex problems, neuroscience contributes novel algorithms and neural network architectures that can endow machines with cognitive abilities. However, direct comparisons between artificial and biological intelligent systems remain limited. We addressed this gap by examining behaviors and neural representations across multiple domains of intelligence. By training mice and deep reinforcement learning (RL) agents on the same tasks and analyzing the resulting task representations in their respective neural networks, we found that learning in the mouse cortex exhibits key features reminiscent of deep RL algorithms. Furthermore, by deriving theoretical predictions from AI models and empirically testing them in mice, we discovered that the brain composes novel behaviors through a simple arithmetic combination of pre-acquired action-value representations and a stochastic policy. These findings underscore the remarkable parallels in behaviors and neural representations between the two systems and highlight the value of comparative approaches.
References:
- Makino, H.*, and Suhaimi, A. 2025. Distributed representations of temporally accumulated reward prediction errors in the mouse cortex. Sci Adv 11, eadi4782.
- Makino, H.* Arithmetic value representation for hierarchical behavior composition. Nat Neurosci 26, 140-149.
- Suhaimi, A., Lim, A.W.H., Chia, X.W., Li, C., and Makino, H.* Representation learning in the artificial and biological neural networks underlying sensorimotor integration. Sci Adv 8, eabn0984.
