Learning and Generalization with Minimerror, A Temperature-Dependent Learning Algorithm

Bruno Raffin; Mirta B. Gordon

doi:10.1162/neco.1995.7.6.1206

More Information

Monthly

288 pp. per issue

6 x 9, illustrated

ISSN

0899-7667

E-ISSN

1530-888X

2014 Impact factor:

2.21

Neural Computation

November 1995, Vol. 7, No. 6, Pages 1206-1224

(doi: 10.1162/neco.1995.7.6.1206)

Learning and Generalization with Minimerror, A Temperature-Dependent Learning Algorithm

Article PDF (811.31 KB)

Bruno Raffin

CEA/Département de Recherche Fondamentale sur la Matière Condensée, SPSMS / MDN, Centre d'Etudes Nucléaires de Grenoble, 17, rue des Martyrs, 38054 Grenoble Cedex 9, France

Mirta B. Gordon

CEA/Département de Recherche Fondamentale sur la Matière Condensée, SPSMS / MDN, Centre d'Etudes Nucléaires de Grenoble, 17, rue des Martyrs, 38054 Grenoble Cedex 9, France

Abstract

We study the numerical performances of Minimerror, a recently introduced learning algorithm for the perceptron that has analytically been shown to be optimal both on learning linearly and nonlinearly separable functions. We present its implementation on learning linearly separable boolean functions. Numerical results are in excellent agreement with the theoretical predictions.