Generalization Ability of Extended Cascaded Artificial Neural Network Architecture

Joarder KAMRUZZAMAN; Yukio KUMAGAI; Hiromitsu HIKITA

Generalization Ability of Extended Cascaded Artificial Neural Network Architecture

Joarder KAMRUZZAMAN, Yukio KUMAGAI, Hiromitsu HIKITA

Full Text Views

0

Cite this

Summary :

We present an extension of the previously proposed 3-layer feedforward network called a cascaded network. Cascaded networks are trained to realize category classification employing binary input vectors and locally represented binary target output vectors. To realize a nonlinearly separable task the extended cascaded network presented here is consreucted by introducing high order cross producted inputs at the input layer. In the construction of the cascaded network, two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be understood as a hidden layer which is trained to attain preassigned saturated outputs in response to the training set. In a cascaded network trained to categorize binary image patterns, saturation of hidden outputs reduces the effect of corrupted disturbances presented in the input. We demonstrated that the extended cascaded network was able to realize a nonlinearly separable task and yielded better generalization ability than the Backpropagation network.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.10 pp.1877-1883

Publication Date: 1993/10/25

Publicized

Online ISSN

DOI

Type of Manuscript: LETTER

Category: Neural Networks

Cite this

Copy

Joarder KAMRUZZAMAN, Yukio KUMAGAI, Hiromitsu HIKITA, "Generalization Ability of Extended Cascaded Artificial Neural Network Architecture" in IEICE TRANSACTIONS on Fundamentals, vol. E76-A, no. 10, pp. 1877-1883, October 1993, doi: .
Abstract: We present an extension of the previously proposed 3-layer feedforward network called a cascaded network. Cascaded networks are trained to realize category classification employing binary input vectors and locally represented binary target output vectors. To realize a nonlinearly separable task the extended cascaded network presented here is consreucted by introducing high order cross producted inputs at the input layer. In the construction of the cascaded network, two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be understood as a hidden layer which is trained to attain preassigned saturated outputs in response to the training set. In a cascaded network trained to categorize binary image patterns, saturation of hidden outputs reduces the effect of corrupted disturbances presented in the input. We demonstrated that the extended cascaded network was able to realize a nonlinearly separable task and yielded better generalization ability than the Backpropagation network.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_10_1877/_p

Copy

@ARTICLE{e76-a_10_1877,
author={Joarder KAMRUZZAMAN, Yukio KUMAGAI, Hiromitsu HIKITA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Generalization Ability of Extended Cascaded Artificial Neural Network Architecture},
year={1993},
volume={E76-A},
number={10},
pages={1877-1883},
abstract={We present an extension of the previously proposed 3-layer feedforward network called a cascaded network. Cascaded networks are trained to realize category classification employing binary input vectors and locally represented binary target output vectors. To realize a nonlinearly separable task the extended cascaded network presented here is consreucted by introducing high order cross producted inputs at the input layer. In the construction of the cascaded network, two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be understood as a hidden layer which is trained to attain preassigned saturated outputs in response to the training set. In a cascaded network trained to categorize binary image patterns, saturation of hidden outputs reduces the effect of corrupted disturbances presented in the input. We demonstrated that the extended cascaded network was able to realize a nonlinearly separable task and yielded better generalization ability than the Backpropagation network.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - Generalization Ability of Extended Cascaded Artificial Neural Network Architecture
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1877
EP - 1883
AU - Joarder KAMRUZZAMAN
AU - Yukio KUMAGAI
AU - Hiromitsu HIKITA
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1993
AB - We present an extension of the previously proposed 3-layer feedforward network called a cascaded network. Cascaded networks are trained to realize category classification employing binary input vectors and locally represented binary target output vectors. To realize a nonlinearly separable task the extended cascaded network presented here is consreucted by introducing high order cross producted inputs at the input layer. In the construction of the cascaded network, two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be understood as a hidden layer which is trained to attain preassigned saturated outputs in response to the training set. In a cascaded network trained to categorize binary image patterns, saturation of hidden outputs reduces the effect of corrupted disturbances presented in the input. We demonstrated that the extended cascaded network was able to realize a nonlinearly separable task and yielded better generalization ability than the Backpropagation network.
ER -