Prediction error of stochastic learning machine

Kazushi Ikeda, Noboru Murata, Shun Ichi Amari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The more the number of training examples increases, the better a learning machine will behave. It is an important problem to know how fast and how well the behavior is improved. The average prediction error is one of the most popular criteria to evaluate the behavior. We have regarded the machine learning from the point of view of parameter estimation and derived the average prediction error of stochastic dichotomy machines by the information geometrical method.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages1159-1162
Number of pages4
Volume2
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

Fingerprint

Learning systems
Parameter estimation

ASJC Scopus subject areas

  • Software

Cite this

Ikeda, K., Murata, N., & Amari, S. I. (1994). Prediction error of stochastic learning machine. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1159-1162). Piscataway, NJ, United States: IEEE.

Prediction error of stochastic learning machine. / Ikeda, Kazushi; Murata, Noboru; Amari, Shun Ichi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 Piscataway, NJ, United States : IEEE, 1994. p. 1159-1162.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ikeda, K, Murata, N & Amari, SI 1994, Prediction error of stochastic learning machine. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, Piscataway, NJ, United States, pp. 1159-1162, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94/6/27.
Ikeda K, Murata N, Amari SI. Prediction error of stochastic learning machine. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. Piscataway, NJ, United States: IEEE. 1994. p. 1159-1162
Ikeda, Kazushi ; Murata, Noboru ; Amari, Shun Ichi. / Prediction error of stochastic learning machine. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 Piscataway, NJ, United States : IEEE, 1994. pp. 1159-1162
@inproceedings{ecc717bacb4a4d7b8f86a86310d5124e,
title = "Prediction error of stochastic learning machine",
abstract = "The more the number of training examples increases, the better a learning machine will behave. It is an important problem to know how fast and how well the behavior is improved. The average prediction error is one of the most popular criteria to evaluate the behavior. We have regarded the machine learning from the point of view of parameter estimation and derived the average prediction error of stochastic dichotomy machines by the information geometrical method.",
author = "Kazushi Ikeda and Noboru Murata and Amari, {Shun Ichi}",
year = "1994",
language = "English",
volume = "2",
pages = "1159--1162",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Prediction error of stochastic learning machine

AU - Ikeda, Kazushi

AU - Murata, Noboru

AU - Amari, Shun Ichi

PY - 1994

Y1 - 1994

N2 - The more the number of training examples increases, the better a learning machine will behave. It is an important problem to know how fast and how well the behavior is improved. The average prediction error is one of the most popular criteria to evaluate the behavior. We have regarded the machine learning from the point of view of parameter estimation and derived the average prediction error of stochastic dichotomy machines by the information geometrical method.

AB - The more the number of training examples increases, the better a learning machine will behave. It is an important problem to know how fast and how well the behavior is improved. The average prediction error is one of the most popular criteria to evaluate the behavior. We have regarded the machine learning from the point of view of parameter estimation and derived the average prediction error of stochastic dichotomy machines by the information geometrical method.

UR - http://www.scopus.com/inward/record.url?scp=0028752567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028752567&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028752567

VL - 2

SP - 1159

EP - 1162

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -