Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Relationship to Neural Learning Rules

Description

This lecture delves into the relationship between neural learning rules and the derivative of the logarithm of a policy, exploring the post-synaptic and pre-synaptic contributions in weight updates. It explains how rewards modulate synaptic weights and how the activity of neurons influences learning.

Official source

Related concepts (27)

Synaptogenesis

Synaptogenesis is the formation of synapses between neurons in the nervous system. Although it occurs throughout a healthy person's lifespan, an explosion of synapse formation occurs during early brain development, known as exuberant synaptogenesis. Synaptogenesis is particularly important during an individual's critical period, during which there is a certain degree of synaptic pruning due to competition for neural growth factors by neurons and synapses.

Long-term depression

In neurophysiology, long-term depression (LTD) is an activity-dependent reduction in the efficacy of neuronal synapses lasting hours or longer following a long patterned stimulus. LTD occurs in many areas of the CNS with varying mechanisms depending upon brain region and developmental progress. As the opposing process to long-term potentiation (LTP), LTD is one of several processes that serves to selectively weaken specific synapses in order to make constructive use of synaptic strengthening caused by LTP.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Feedforward neural network

A feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.

Activity-dependent plasticity

Activity-dependent plasticity is a form of functional and structural neuroplasticity that arises from the use of cognitive functions and personal experience; hence, it is the biological basis for learning and the formation of new memories. Activity-dependent plasticity is a form of neuroplasticity that arises from intrinsic or endogenous activity, as opposed to forms of neuroplasticity that arise from extrinsic or exogenous factors, such as electrical brain stimulation- or drug-induced neuroplasticity.

Related lectures (49)

Neural Networks: Multilayer Perceptrons

Covers Multilayer Perceptrons, artificial neurons, activation functions, matrix notation, flexibility, regularization, regression, and classification tasks.

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

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

Deep Neural Networks: Optimization and Approximation

Explores optimization and approximation in deep neural networks, including optimal control and numerical experiments.

Dynamics of Linear Neural Networks