Limitations on Complexity of Random Learning Networks

Randomly connected networks can be made adaptive, and thus able to “learn.” Signal-to-noise considerations are shown to limit the maximum initial complexity which can learn. A higher order of complexity may be possible in multilayered structures which learn layer-by-layer; or if learning is possible...

Full description

Saved in:
Bibliographic Details
Published in:Biophysical journal 1965-03, Vol.5 (2), p.195-200
Main Author: Offner, Franklin
Format: Article
Language:English
Subjects:
Computers
Computers, Analog
Cybernetics
Humans
Learning
Mathematics
Neurophysiology
Old Medline
Sensory Receptor Cells
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Randomly connected networks can be made adaptive, and thus able to “learn.” Signal-to-noise considerations are shown to limit the maximum initial complexity which can learn. A higher order of complexity may be possible in multilayered structures which learn layer-by-layer; or if learning is possible during construction. Perception-like devices would appear not to be operative if of a high order of complexity.
ISSN:0006-3495
1542-0086
DOI:10.1016/S0006-3495(65)86710-8