neuron

The basic computational unit of an artificial neural network, which applies an activation function to a weighted sum of its inputs.

1 articleLast mentioned

A neuron is the basic computational unit of an artificial neural network. It multiplies each of its inputs by a weight, sums the results, and applies an activation function to produce a single output value, or activation; a neural network consists of layers of such neurons connected together. Neurons are also called units or nodes.

The artificial neuron is a simplified model of the biological nerve cell, originating in the mathematical model proposed by Warren McCulloch and Walter Pitts in 1943 and in Frank Rosenblatt's perceptron of 1958. Interpretability research analyzes which input features individual neurons respond to, and polysemanticity, in which one neuron responds to several unrelated features, is a central topic. In biology, the term refers to the nerve cells that transmit information through electrical signals.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Neural Networks Are Already Clean: Study Claims 90% of Neuron Poles Are LegibleAI Security ·

    According to the essay, roughly 90 percent of neuron poles in a modern language model perform a single, human-readable job, and the messy "polysemantic" neurons…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.