Principles of Self-Organization

Description

This lecture covers the principles of self-organization in neural networks, focusing on how global order emerges from local interactions. Topics include receptive field development, Oja's Rule, ocular dominance columns, Kohonen Maps, and the functional role of cortical maps.

In MOOCs (3)

Official source

https://mediaspace.epfl.ch/media/0_a59b8550

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (5)

Related concepts (21)

Cortical homunculus

A cortical homunculus () is a distorted representation of the human body, based on a neurological "map" of the areas and proportions of the human brain dedicated to processing motor functions, or sensory functions, for different parts of the body. Nerve fibresconducting somatosensory information from all over the bodyterminate in various areas of the parietal lobe in the cerebral cortex, forming a representational map of the body. Findings from the 2010s and early 2020s began to call this interpretation into question, and research is ongoing in this field.

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.

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.

Cortical stimulation mapping

Cortical stimulation mapping (CSM) is a type of electrocorticography that involves a physically invasive procedure and aims to localize the function of specific brain regions through direct electrical stimulation of the cerebral cortex. It remains one of the earliest methods of analyzing the brain and has allowed researchers to study the relationship between cortical structure and systemic function.

Motor cortex

The motor cortex is the region of the cerebral cortex involved in the planning, control, and execution of voluntary movements. The motor cortex is an area of the frontal lobe located in the posterior precentral gyrus immediately anterior to the central sulcus. The motor cortex can be divided into three areas: 1. The primary motor cortex is the main contributor to generating neural impulses that pass down to the spinal cord and control the execution of movement. However, some of the other motor areas in the brain also play a role in this function.