DocumentCode
2259478
Title
Realization of limit cycles by neural networks with piecewise linear activation function
Author
Takahashi, Norikazu ; Yamakawa, Tsuyoshi ; Nishi, Tetsuo
Author_Institution
Dept. of Comput. Sci. & Commun. Eng., Kyushu Univ., Fukuoka, Japan
Volume
3
fYear
2005
fDate
28 Aug.-2 Sept. 2005
Abstract
A simple method of realizing a prescribed limit cycle by means of a continuous-time recurrent neural network with the piecewise-linear activation function is proposed. Since the proposed method is formulated as a set of linear inequalities, we can easily determine parameters of the network by using, for example, the simplex method.
Keywords
neural nets; piecewise linear techniques; continuous time recurrent neural network; limit cycles; linear inequalities; network parameters; piecewise linear activation function; Associative memory; Computer science; Design methodology; Electronic mail; Learning systems; Limit-cycles; Linear programming; Neural networks; Piecewise linear techniques; Recurrent neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuit Theory and Design, 2005. Proceedings of the 2005 European Conference on
Print_ISBN
0-7803-9066-0
Type
conf
DOI
10.1109/ECCTD.2005.1523047
Filename
1523047
Link To Document