Learning by choice of internal representations- Feed forward nets with binary weights

D. Saad, E. Marom

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Learning by choice of internal representations (CHIR) is a training algorithm for feed-forward(FF) neural networks, introduced by Grossman et alt [2], based upon determining the internal representations of the system as well as its internal weights. In a former paper[3] we have shown a method for deriving the CHIR algorithm, whereby the internal representations (IR) as well as the weights are allowed to be modified, via energy minimization consideration. This method is now applied for training a FF net with binary weights, supplying a convenient tool for training such a net. Computer simulations show a fast training process for this algorithm in comparison with the Back-Propagation[4] and the CHIR[1][2] algorithms, both used in conjunction with a feed-forward net with continuous weights. These simulations include the restricted cases of parity, symmetry and parity-symmetry problems.

Original languageEnglish
Title of host publicationProceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages199-202
Number of pages4
ISBN (Electronic)0879426780, 9780879426781
DOIs
StatePublished - 1991
Event17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991 - Tel Aviv, Israel
Duration: 5 Mar 19917 Mar 1991

Publication series

NameProceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

Conference

Conference17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
Country/TerritoryIsrael
CityTel Aviv
Period5/03/917/03/91

Fingerprint

Dive into the research topics of 'Learning by choice of internal representations- Feed forward nets with binary weights'. Together they form a unique fingerprint.

Cite this