Title :
Simple activation functions for neural and fuzzy neural networks
Author :
Mendil, Boubekeur ; Benmahammed, K.
Author_Institution :
Dept. of Electr. Eng., Bejaia Univ., Algeria
Abstract :
In this paper, we propose some activation functions designed to simplify the computational complexity and the hardware implementation of neural and fuzzy neural networks. These functions approximate the sigmoidal and the Gaussian shapes using only simple arithmetic operations. The simulation results show the good approximation capabilities of the resulting networks
Keywords :
computational complexity; fuzzy neural nets; neural nets; transfer functions; Gaussian shapes; activation functions; approximation capabilities; arithmetic operations; computational complexity; fuzzy neural networks; hardware implementation; neural networks; sigmoidal shapes; Arithmetic; Artificial intelligence; Biological neural networks; Brain modeling; Computational modeling; Costs; Fuzzy neural networks; Humans; Mathematical model; Neurons;
Conference_Titel :
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-5471-0
DOI :
10.1109/ISCAS.1999.777580
