The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Aplicamos duas técnicas de aceleração para o algoritmo de retropropagação a um algoritmo iterativo de descida de gradiente denominado algoritmo de inversão de rede. Resultados experimentais mostram que estas técnicas também são bastante eficazes para diminuir o número de iterações necessárias para a detecção de vetores de entrada na fronteira de classificação de um perceptron multicamadas.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hiroyuki TAKIZAWA, Taira NAKAJIMA, Masaaki NISHI, Hiroaki KOBAYASHI, Tadao NAKAMURA, "Acceleration Techniques for the Network Inversion Algorithm" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 2, pp. 508-511, February 1999, doi: .
Abstract: We apply two acceleration techniques for the backpropagation algorithm to an iterative gradient descent algorithm called the network inversion algorithm. Experimental results show that these techniques are also quite effective to decrease the number of iterations required for the detection of input vectors on the classification boundary of a multilayer perceptron.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_2_508/_p
Copiar
@ARTICLE{e82-d_2_508,
author={Hiroyuki TAKIZAWA, Taira NAKAJIMA, Masaaki NISHI, Hiroaki KOBAYASHI, Tadao NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Acceleration Techniques for the Network Inversion Algorithm},
year={1999},
volume={E82-D},
number={2},
pages={508-511},
abstract={We apply two acceleration techniques for the backpropagation algorithm to an iterative gradient descent algorithm called the network inversion algorithm. Experimental results show that these techniques are also quite effective to decrease the number of iterations required for the detection of input vectors on the classification boundary of a multilayer perceptron.},
keywords={},
doi={},
ISSN={},
month={February},}
Copiar
TY - JOUR
TI - Acceleration Techniques for the Network Inversion Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 508
EP - 511
AU - Hiroyuki TAKIZAWA
AU - Taira NAKAJIMA
AU - Masaaki NISHI
AU - Hiroaki KOBAYASHI
AU - Tadao NAKAMURA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1999
AB - We apply two acceleration techniques for the backpropagation algorithm to an iterative gradient descent algorithm called the network inversion algorithm. Experimental results show that these techniques are also quite effective to decrease the number of iterations required for the detection of input vectors on the classification boundary of a multilayer perceptron.
ER -