A multilayer feedforward neural network having N/4 nodes in two hidden layers

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In order to reduce the complexity of a single hidden layered multilayer neural network, a new two hidden layered MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2 = 18 hidden nodes and 34 weights is equal to that of an optimaum Bayesian equalizer using an RBFN with P = 64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by theoretical approach, and the feasibility of a more reduced structure is given.

Original languageEnglish
Pages1675-1680
Number of pages6
Publication statusPublished - 2001 Jan 1
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Feedforward neural networks
Multilayer neural networks
Equalizers

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Choi, S., Ko, K., & Hong, D. (2001). A multilayer feedforward neural network having N/4 nodes in two hidden layers. 1675-1680. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.
Choi, S. ; Ko, K. ; Hong, D. / A multilayer feedforward neural network having N/4 nodes in two hidden layers. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.6 p.
@conference{0d796cc0011047b0a508c0ab73f2c7c9,
title = "A multilayer feedforward neural network having N/4 nodes in two hidden layers",
abstract = "In order to reduce the complexity of a single hidden layered multilayer neural network, a new two hidden layered MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2 = 18 hidden nodes and 34 weights is equal to that of an optimaum Bayesian equalizer using an RBFN with P = 64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by theoretical approach, and the feasibility of a more reduced structure is given.",
author = "S. Choi and K. Ko and D. Hong",
year = "2001",
month = "1",
day = "1",
language = "English",
pages = "1675--1680",
note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

Choi, S, Ko, K & Hong, D 2001, 'A multilayer feedforward neural network having N/4 nodes in two hidden layers' Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States, 01/7/15 - 01/7/19, pp. 1675-1680.

A multilayer feedforward neural network having N/4 nodes in two hidden layers. / Choi, S.; Ko, K.; Hong, D.

2001. 1675-1680 Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A multilayer feedforward neural network having N/4 nodes in two hidden layers

AU - Choi, S.

AU - Ko, K.

AU - Hong, D.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - In order to reduce the complexity of a single hidden layered multilayer neural network, a new two hidden layered MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2 = 18 hidden nodes and 34 weights is equal to that of an optimaum Bayesian equalizer using an RBFN with P = 64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by theoretical approach, and the feasibility of a more reduced structure is given.

AB - In order to reduce the complexity of a single hidden layered multilayer neural network, a new two hidden layered MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2 = 18 hidden nodes and 34 weights is equal to that of an optimaum Bayesian equalizer using an RBFN with P = 64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by theoretical approach, and the feasibility of a more reduced structure is given.

UR - http://www.scopus.com/inward/record.url?scp=0034870434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034870434&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034870434

SP - 1675

EP - 1680

ER -

Choi S, Ko K, Hong D. A multilayer feedforward neural network having N/4 nodes in two hidden layers. 2001. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.