Computing Higher Order Derivatives in Universal Learning Networks

Kotaro Hirasawa; Jinglu Hu; Masanao Ohbayashi; Junichi Murata

doi:10.20965/jaciii.1998.p0047

single-jc.php

« previous

JACIII Vol.2 No.2 pp. 47-53

doi: 10.20965/jaciii.1998.p0047

(1998)

Paper:

Views over last 60 days: 309

Computing Higher Order Derivatives in Universal Learning Networks

Kotaro Hirasawa, Jinglu Hu, Masanao Ohbayashi, and Junichi Murata

Department of Electrical and Electronic Systems Engineering, Kyushu University. Hakozaki, Fukuoka 812-81, Japan

Received:

October 27, 1997

Accepted:

March 3, 1998

Published:

April 20, 1998

Keywords:

learning network, neural network, higher order derivative, backward propagation, forward propagation

Abstract

This paper discusses higher order derivative computing for universal learning networks that form a super set of all kinds of neural networks. Two computing algorithms, backward and forward propagation, are proposed. Using a technique called “local description” expresses the proposed algorithms very simply. Numerical simulations demonstrate the usefulness of higher order derivatives in neural network training.

Cite this article as:

Kotaro Hirasawa, Jinglu Hu, Masanao Ohbayashi, and Junichi Murata, “Computing Higher Order Derivatives in Universal Learning Networks,” J. Adv. Comput. Intell. Intell. Inform., Vol.2, No.2, pp. 47-53, 1998.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.