Interval-valued differential evolution for evolving neural networks with interval weights and biases

Author

Okada, H.

Author_Institution

Fac. of Comput. Sci. & Eng., Kyoto Sangyo Univ., Kyoto, Japan

fYear

2013

fDate

13-13 July 2013

Firstpage

81

Lastpage

84

Abstract

The ordinary differential evolution (DE) algorithm employs real-valued vectors as genotypes. The author previously proposed an extension of DE which can handle interval-valued genotypes. In this paper, the proposed method is applied to evolution of neural networks with interval connection weights and biases. Experimental results show that the interval DE can evolve neural networks which model interval functions well despite that no training data is explicitly provided.

Keywords

evolutionary computation; feedforward neural nets; vectors; DE algorithm; DE extension; evolving neural networks; genotypes; interval connection biases; interval connection weights; interval-valued differential evolution; multilayered feedforward neural network; real-valued vectors; Artificial neural networks; Evolutionary computation; Gold; Sociology; Statistics; Vectors; differential evolution; evolutionary algorithms; interval arithmetic; neural network; neuroevolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence & Applications (IWCIA), 2013 IEEE Sixth International Workshop on

Conference_Location

Hiroshima

ISSN

1883-3977

Print_ISBN

978-1-4673-5725-8

Type

conf

DOI

10.1109/IWCIA.2013.6624789

Filename

6624789