Lecture

Analyzing Hebbian Learning Rule

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 delves into the analysis of Hebbian learning rules, focusing on rate-based Hebbian learning and the application of Taylor expansion to determine the change of weights based on pre- and post-synaptic firing rates. It also covers Hebbian learning rate models, Oja's rule, post-synaptic and pre-synaptic thresholds, and the covariance rule. The presentation includes a discussion on the covariance matrix and the growth of weight vectors in the context of Hebbian learning.

Official source

Related concepts (25)

Hebbian theory

Hebbian theory is a neuropsychological theory claiming that an increase in synaptic efficacy arises from a presynaptic cell's repeated and persistent stimulation of a postsynaptic cell. It is an attempt to explain synaptic plasticity, the adaptation of brain neurons during the learning process. It was introduced by Donald Hebb in his 1949 book The Organization of Behavior. The theory is also called Hebb's rule, Hebb's postulate, and cell assembly theory.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Synaptic vesicle

In a neuron, synaptic vesicles (or neurotransmitter vesicles) store various neurotransmitters that are released at the synapse. The release is regulated by a voltage-dependent calcium channel. Vesicles are essential for propagating nerve impulses between neurons and are constantly recreated by the cell. The area in the axon that holds groups of vesicles is an axon terminal or "terminal bouton". Up to 130 vesicles can be released per bouton over a ten-minute period of stimulation at 0.2 Hz.

Neural network

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Related lectures (64)

Neuromorphic Computing: Concepts and Hardware Implementations

Covers neuromorphic computing, challenges in ternary and binary computing, hardware simulations of the brain, and new materials for artificial brain cells.

Synaptic Transmission: Electrical vs Chemical

Compares electrical and chemical synapses, emphasizing their properties and behavior, including the neuromuscular junction and synapses in the CNS.

Neuronal Plasticity: Synaptic Changes and Brain Functioning

Explores neuronal plasticity, synaptic changes, brain functioning, and unconscious states through various mechanisms.

Building Physical Neural Networks

Discusses challenges in building physical neural networks, focusing on depth, connections, and trainability.

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