Fractal connection structure: effect on generalization in supervised feed-forward networks

Author

Chakraborty, Basabi ; Sawada, Yasuji

Author_Institution

Res. Inst. of Electr. Commun., Tohoku Univ., Sendai, Japan

Volume

1

fYear

1996

fDate

3-6 Jun 1996

Firstpage

264

Abstract

Fractal connection structure within the layers of a multilayered feedforward net has been studied in this paper. Fractal connection structure ensures modularity, easy hardware implementation and resembles biological neural system more closely than fully connected layered architecture. Simulation on sonar signal for underwater target classification problem shows that fractal net with fractal dimension around .9 with average connectivity 80% performs better than the fully connected net of same size (same number of neurons) in terms of classification accuracy and generalization behaviour to unseen samples

Keywords

feedforward neural nets; fractals; generalisation (artificial intelligence); multilayer perceptrons; neural net architecture; biological neural system; classification accuracy; fractal connection structure; fractal net; generalization; modularity; multilayered feedforward net; sonar signal; supervised feed-forward networks; underwater target classification; Biological neural networks; Biological system modeling; Feedforward systems; Fractals; Hardware; Humans; Intelligent networks; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.548902

Filename

548902