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

Author

Choi, Sooyong ; Ko, Kyunbyoung ; Hong, Daesik

Author_Institution

Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea

Volume

3

fYear

2001

fDate

2001

Firstpage

1675

Abstract

In order to reduce the complexity of a single hidden layer multilayer neural network, a new two hidden layer 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 optimum 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 a theoretical approach, and the feasibility of a more reduced structure is given

Keywords

learning (artificial intelligence); multilayer perceptrons; radial basis function networks; feedforward neural network; hidden nodes; learning; multilayer neural network; multilayer perceptron; online recursive methods; radial basis function network; Bayesian methods; Electronic mail; Equalizers; Equations; Feedforward neural networks; Intelligent networks; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-7044-9

Type

conf

DOI

10.1109/IJCNN.2001.938413

Filename

938413