A Biologically Plausible Learning Rule for Perceptual Systems of organisms that Maximize Mutual Information
Neural and Evolutionary Computing
2021-10-06 v2 Artificial Intelligence
Neurons and Cognition
Abstract
It is widely believed that the perceptual system of an organism is optimized for the properties of the environment to which it is exposed. A specific instance of this principle known as the Infomax principle holds that the purpose of early perceptual processing is to maximize the mutual information between the neural coding and the incoming sensory signal. In this article, we present a method to implement this principle accurately with a local, spike-based, and continuous-time learning rule.
Keywords
Cite
@article{arxiv.2109.13102,
title = {A Biologically Plausible Learning Rule for Perceptual Systems of organisms that Maximize Mutual Information},
author = {Tao Liu},
journal= {arXiv preprint arXiv:2109.13102},
year = {2021}
}