Binary Perceptron Learning Algorithm Using Simplex-Method

A number of researchers headed by E. Gardner have proved that a maximum achievable memory load of binary perceptron is 2. A learning algorithm allowing reaching and even exceeding the critical load was proposed. The algorithm was reduced to solving the linear programming problem. The proposed algori...

Full description

Saved in:
Bibliographic Details
Published inArtificial Intelligence and Soft Computing pp. 111 - 118
Main Authors Kryzhanovskiy, Vladimir, Zhelavskaya, Irina, Karandashev, Jakov
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2012
SeriesLecture Notes in Computer Science
Subjects
Binary neural networks
simplex-method
Online AccessGet full text
ISBN3642293468
9783642293467
ISSN0302-9743
1611-3349
DOI10.1007/978-3-642-29347-4_13

Cover

More Information
Summary:A number of researchers headed by E. Gardner have proved that a maximum achievable memory load of binary perceptron is 2. A learning algorithm allowing reaching and even exceeding the critical load was proposed. The algorithm was reduced to solving the linear programming problem. The proposed algorithm is sequel to Krauth and Mezard ideas. The algorithm makes it possible to construct networks storage capacity and noise stability of which are comparable to those of Krauth and Mezard algorithm. However suggested modification of the algorithm outperforms.
ISBN:3642293468
9783642293467
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-29347-4_13