Neurons as autoencoders

Bull, Larry

Abstract

This letter presents the idea that neural backpropagation is exploiting dendritic processing to enable individual neurons to perform autoencoding. Using a very simple connection weight search heuristic and artificial neural network model, the effects of interleaving autoencoding for each neuron in a hidden layer of a feedforward network are explored. This is contrasted with the equivalent standard layered approach to autoencoding. It is shown that such individualised processing is not detrimental and can improve network learning.

• Journal Article Type: Article
• Acceptance Date: Aug 20, 2024
• Online Publication Date: Nov 13, 2024
• Deposit Date: Aug 23, 2024
• Publicly Available Date: Nov 13, 2024
• Print ISSN: 1064-5462
• Electronic ISSN: 1530-9185
• Publisher: Massachusetts Institute of Technology Press (MIT Press)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1162/artl_c_00461
• Keywords: autoencoder; backpropagation; dendrite; multi-layer perceptron; neuron
• Public URL: https://uwe-repository.worktribe.com/output/12804243