Local Learning Rules: Representations and Actions

This lecture explores local learning rules for learning representations and actions, focusing on synaptic plasticity and behavioral learning. It discusses the framework of Hebbian learning, the insufficiency of Hebbian learning alone, and the importance of eligibility traces and dopamine in reinforcement learning. The lecture also covers three-factor rules for reinforcement learning, illustrated through examples like the Maze task. It delves into the specificity of three-factor rules with neuromodulators and the concept of good representations for navigation and object recognition. The presentation concludes with discussions on self-supervision, contrastive learning, and the CLAPP model for plasticity, emphasizing the importance of local neo-Hebbian learning rules.