Lecture

Local Learning Rules: Representations and Actions

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

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.

Official source

Related concepts (32)

Self-supervised learning

Self-supervised learning (SSL) is a paradigm in machine learning for processing data of lower quality, rather than improving ultimate outcomes. Self-supervised learning more closely imitates the way humans learn to classify objects. The typical SSL method is based on an artificial neural network or other model such as a decision list. The model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels which help to initialize the model parameters.

Unsupervised learning

Unsupervised learning, is paradigm in machine learning where, in contrast to supervised learning and semi-supervised learning, algorithms learn patterns exclusively from unlabeled data. Neural network tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see Venn diagram); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups.

Synaptic plasticity

In neuroscience, synaptic plasticity is the ability of synapses to strengthen or weaken over time, in response to increases or decreases in their activity. Since memories are postulated to be represented by vastly interconnected neural circuits in the brain, synaptic plasticity is one of the important neurochemical foundations of learning and memory (see Hebbian theory). Plastic change often results from the alteration of the number of neurotransmitter receptors located on a synapse.

Feature learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.

Related lectures (64)

Classification of Plasticity: Short-term vs. Long-term Changes MOOC: Neuronal Dynamics 2- Computational Neuroscience: Neuronal Dynamics of Cognition

Explores short-term and long-term synaptic changes, Hebbian learning, and the role of neuromodulators.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Introduction to synaptic plasticity MOOC: Simulating a hippocampus micro-circuit

Covers synaptic plasticity, types of synapses, Hebb's postulate, LTP, LTD, and network oscillations in the hippocampus.

Machine Learning Fundamentals

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.

Self-supervised Learning for Autonomous Vehicles