Search

Advanced Search

Find results with:

Add another field

Search by date

to

Searching collections:

Institutional Repository

Add or remove collections

Home Institutional Repository Improved Hopfield Networks by Training with Noisy Data

Rate

To link to this object, paste this link in email, IM or document

To embed this object, paste this HTML in website

Improved Hopfield Networks by Training with Noisy Data

View Description

Download

small (250x250 max)

medium (500x500 max)

large ( > 500x500)

Full Resolution

Print

PDF
Text

Description

Rating
Permanent URL	http://hdl.lib.byu.edu/1877/2426
Title	Improved Hopfield Networks by Training with Noisy Data
BYU Creator	Clift, Fred Martinez, Tony R.
Keywords	Hopfield network; back-propagation; noisy associative training
Description/Abstract	A new approach to training a generalized Hopfield network is developed and evaluated in this work. Both the weight symmetricity constraint and the zero self-connection constraint are removed from standard Hopfield networks. Training is accomplished with Back-Propagation Through Time, using noisy versions of the memorized patterns. Training in this way is referred to as Noisy Associative Training (NAT). Performance of NAT is evaluated on both random and correlated data. NAT has been tested on several data sets, with a large number of training runs for each experiment. The data sets used include uniformly distributed random data and several data sets adapted from the U.C. Irvine Machine Learning Repository. Results show that for random patterns, Hopfield networks trained with NAT have an average overall recall accuracy 6.1 times greater than networks produced with either Hebbian or Pseudo-Inverse training. Additionally, these networks have 13% fewer spurious memories on average than networks trained with Pseudo-Inverse or Hebbian training. Typically, networks memorizing over 2N (where N is the number of nodes in the network) patterns are produced. Performance on correlated data shows an even greater improvement over networks produced with either Hebbian or Pseudo-Inverse training - An average of 27.8 times greater recall accuracy, with 14% fewer spurious memories.
Source	Clift, F. and Martinez, T. R., "Improved Hopfield Networks by Training with Noisy Data", Proceedings of the IEEE International Joint Conference on Neural Networks IJCNN'01, pp. 1138-1143, 2001.;
Publisher	IEEE
Date Original	2001
Date Digital	2010-09-09
Language	English eng en
Publication Type	Peer-Reviewed Articles Conference Proceedings
Type	Text
Format	application/pdf
Owning Institution	Brigham Young University
BYU College	College of Physical and Mathematical Sciences
BYU Department	Computer Science
Copyright Status	(c) 2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.;
Copyright Use Information	http://www.lib.byu.edu/generic_copyright.html

Tags

Add tags for Improved Hopfield Networks by Training with Noisy Data

View as list | View as tag cloud | report abuse

Comments

Post a Comment for Improved Hopfield Networks by Training with Noisy Data

you wish to report:

Your comment:

Your Name:

Submit

Cancel

...

Powered by CONTENTdm®