Meta-Learning Through Hebbian Plasticity in Random Networks - Paper Explained
Offered By: Yannic Kilcher via YouTube
Course Description
Overview
Explore a comprehensive analysis of a research paper on meta-learning through Hebbian plasticity in random networks in this 39-minute video. Delve into the comparison between reinforcement learning and Hebbian plasticity, understand the concept of episodes in Hebbian learning, and examine Hebbian plasticity rules. Discover the results of quadruped experiments and the evolutionary learning of Hebbian plasticity. Gain insights into additional experimental findings, conclusions, and the broader impact of this research. Learn how biologically-inspired Hebbian learning techniques enable agents to adapt random networks to high-performing solutions during an episode, allowing for quick reconfiguration in response to new observations.
Syllabus
- Intro & Overview
- Reinforcement Learning vs Hebbian Plasticity
- Episodes in Hebbian Learning
- Hebbian Plasticity Rules
- Quadruped Experiment Results
- Evolutionary Learning of Hebbian Plasticity
- More Experimental Results
- Conclusions
- Broader Impact Statement
Taught by
Yannic Kilcher
Related Courses
Basic Behavioral NeurologyUniversity of Pennsylvania via Coursera Neuroethics
University of Pennsylvania via Coursera Medical Neuroscience
Duke University via Coursera Drugs and the Brain
California Institute of Technology via Coursera Computational Neuroscience
University of Washington via Coursera