An Algorithm to Compute the Admissible Parameter Region of a Single-Layered Perceptron

Issei SHINOHARA; Syunichirou KIKUCHI; Yasuaki OISHI; Hidenori KIMURA

doi:10.9746/sicetr1965.36.622

Issei SHINOHARA, Syunichirou KIKUCHI, Yasuaki OISHI, Hidenori KIMURA

Author information

Keywords: single-layered perceptron, Bayesian statistics, statistical mechanics, admissible region, linear programming

JOURNAL FREE ACCESS

2000 Volume 36 Issue 7 Pages 622-624

DOI https://doi.org/10.9746/sicetr1965.36.622

Details

Abstract

This paper provides an algorithm to compute the admissible parameter region in the learning by a single-layered perceptron. This algorithm is carried out by solving linear programming problems, the number of which is proportional to that of given samples.

Corresponding author

Register with J-STAGE for free!