English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  On the Asymptotic Information Storage Capacity of Neural Networks

Palm, G. (1989). On the Asymptotic Information Storage Capacity of Neural Networks. In R. Eckmiller, & C. von der Malsburg (Eds.), Neural Computers (pp. 271-280). Berlin, Germany: Springer.

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Palm, G1, 2, Author              
Affiliations:
1Former Department Structure and Function of Natural Nerve-Net , Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497803              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Neural networks can be useful and economic as associative memories, even in technical applications. The asymptotic information storage capacity of such neural networks is defined and then calculated and compared for various local synaptic rules. It turns out that among these rules the simple Hebb rule is optimal in terms of its storage capacity. Furthermore the capacity of the clipped Hebb rule (C = In 2) is even higher than the capacity of the unclipped Hebb rule (C = 1/(8-ln 2)).

Details

show
hide
Language(s):
 Dates: 1989
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-642-83740-1_29
 Degree: -

Event

show
hide
Title: NATO Advanced Research Workshop on Neural Computers
Place of Event: Neuss, Germany
Start-/End Date: 1987-09-28 - 1987-10-02

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural Computers
Source Genre: Proceedings
 Creator(s):
Eckmiller, R, Editor
von der Malsburg, C, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: 566 Volume / Issue: - Sequence Number: - Start / End Page: 271 - 280 Identifier: ISBN: 3-540-50892-9

Source 2

show
hide
Title: Springer Study Edition
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 41 Sequence Number: - Start / End Page: - Identifier: -