Neural Networks Learn Highly Selective Representations in Order to Overcome the Superposition Catastrophe.

A key insight from 50 years of neurophysiology is that some neurons in cortex respond to information in a highly selective manner. Why is this? We argue that selective representations support the coactivation of multiple "things" (e.g., words, objects, faces) in short-term memory, whereas nonselecti...

Full description

Bibliographic Details

Published in:	Psychological Review Vol. 121; no. 2; pp. 248 - 262
Main Authors:	Bowers, Jeffrey S., Vankov, Ivan I., Damian, Markus F., Davis, Colin J.
Format:	Article
Published:	American Psychological Association Apr2014
Subjects:	Neurophysiology Neurons Short-term memory Cerebral cortex Biological neural networks
Online Access:	View this record in EBSCOhost