Multi-gradient

A fast converging and high performance learning algorithm

Chulhee Lee, Jinwook Go

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In this paper, we propose a new learning algorithm for multilayer neural networks. In the backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the difference between the computed and desired outputs. In the proposed learning algorithm, we consider each term of the output layer as a function of weights and adjust the weights directly so that the output layers produce the desired outputs. Experiments show the proposed algorithm consistently performs better than the back-propagation learning algorithm.

Original languageEnglish
Pages1721-1724
Number of pages4
Publication statusPublished - 1999 Dec 1
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 1999 Jul 101999 Jul 16

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period99/7/1099/7/16

Fingerprint

Learning algorithms
Backpropagation algorithms
Multilayer neural networks
Backpropagation
Cost functions
Experiments

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Lee, C., & Go, J. (1999). Multi-gradient: A fast converging and high performance learning algorithm. 1721-1724. Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .
Lee, Chulhee ; Go, Jinwook. / Multi-gradient : A fast converging and high performance learning algorithm. Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .4 p.
@conference{419ecd0ddbb147d2a016db0ba4b2e4c4,
title = "Multi-gradient: A fast converging and high performance learning algorithm",
abstract = "In this paper, we propose a new learning algorithm for multilayer neural networks. In the backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the difference between the computed and desired outputs. In the proposed learning algorithm, we consider each term of the output layer as a function of weights and adjust the weights directly so that the output layers produce the desired outputs. Experiments show the proposed algorithm consistently performs better than the back-propagation learning algorithm.",
author = "Chulhee Lee and Jinwook Go",
year = "1999",
month = "12",
day = "1",
language = "English",
pages = "1721--1724",
note = "International Joint Conference on Neural Networks (IJCNN'99) ; Conference date: 10-07-1999 Through 16-07-1999",

}

Lee, C & Go, J 1999, 'Multi-gradient: A fast converging and high performance learning algorithm' Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, 99/7/10 - 99/7/16, pp. 1721-1724.

Multi-gradient : A fast converging and high performance learning algorithm. / Lee, Chulhee; Go, Jinwook.

1999. 1721-1724 Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Multi-gradient

T2 - A fast converging and high performance learning algorithm

AU - Lee, Chulhee

AU - Go, Jinwook

PY - 1999/12/1

Y1 - 1999/12/1

N2 - In this paper, we propose a new learning algorithm for multilayer neural networks. In the backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the difference between the computed and desired outputs. In the proposed learning algorithm, we consider each term of the output layer as a function of weights and adjust the weights directly so that the output layers produce the desired outputs. Experiments show the proposed algorithm consistently performs better than the back-propagation learning algorithm.

AB - In this paper, we propose a new learning algorithm for multilayer neural networks. In the backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the difference between the computed and desired outputs. In the proposed learning algorithm, we consider each term of the output layer as a function of weights and adjust the weights directly so that the output layers produce the desired outputs. Experiments show the proposed algorithm consistently performs better than the back-propagation learning algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0033308114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033308114&partnerID=8YFLogxK

M3 - Paper

SP - 1721

EP - 1724

ER -

Lee C, Go J. Multi-gradient: A fast converging and high performance learning algorithm. 1999. Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .