An extended procedure of constructing neural networks for supervised dichotomy

Author

Lee, Shie-Jue ; Jone, Mu-Tune

Author_Institution

Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan

Volume

Issue

fYear

1996

fDate

8/1/1996 12:00:00 AM

Firstpage

660

Lastpage

665

Abstract

K.J. Clos and N. Liu (1992) proposed a neural network generation procedure for supervised two-class discretization based on a continuous ID3 algorithm. The method constructs neural networks consisting of neurons with linear activation functions. We extend the procedure to allow decision boundaries to be any arbitrary function. The advantage of the extension is revealed by the decrease in size of the generated neural networks

Keywords

learning (artificial intelligence); neural nets; polynomials; transfer functions; arbitrary function; continuous ID3 algorithm; decision boundaries; linear activation functions; neural networks; supervised dichotomy; supervised two-class discretization; Buildings; Councils; Data structures; Information entropy; Neural networks; Neurons; Polynomials; Simulated annealing; Spirals; Sun;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/3477.517042

Filename

517042

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1145509