DocumentCode :
673294
Title :
Application of global-extreme-learning to law-discovery neural networks
Author :
Majewski, J. ; Wojtyna, Ryszard
Author_Institution :
Fac. of Telecommun., Comput. Sci. & Electr. Eng., Univ. of Technol. & Life Sci., Bydgoszcz, Poland
fYear :
2013
fDate :
26-28 Sept. 2013
Firstpage :
56
Lastpage :
60
Abstract :
The problem of improving efficiency of training special-type neural networks (SNN) used to create symbolic description of rules governing a set of empirical data is considered. Values of the description parameters are determined by the network training. Difficulties with the SNN learning appear mainly due to a great number of local minima encountered in this process. The learning methods we applied so far were based on a modified version the Back Propagation algorithm called BP-CM-BFGS. It turned out, however, that this approach is not always effective, especially when the number of input variables of the SNN increases. In this paper, we propose to use as training technique an evaluation algorithm called Differential Evolution (DE). To illustrate effectiveness of this technique we present results of learning a reciprocal-function-based SNN [15] implementing a fifth order polynomial.
Keywords :
backpropagation; evolutionary computation; neural nets; polynomials; BP-CM-BFGS; DE; SNN training; back propagation algorithm; differential evolution; fifth order polynomial; global-extreme-learning; law-discovery neural networks; local minima; reciprocal-function-based SNN; special-type neural network training; symbolic description; Artificial neural networks; Polynomials; Silicon; Neural networks; global training; rules governing numerical data; symbolic description methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2013
Conference_Location :
Poznan
ISSN :
2326-0262
Electronic_ISBN :
2326-0262
Type :
conf
Filename :
6710596
Link To Document :
بازگشت