Title :
A simultaneous learning method for both activation functions and connection weights of multilayer neural networks
Author :
Nakayama, Kenji ; Ohsugi, Moritomo
Author_Institution :
Dept. of Electr. & Comput. Eng., Kanazawa Univ., Japan
Abstract :
This paper proposes a simultaneous learning algorithm for both activation functions and connection weights. The activation function is composed of several basic functions, such as sigmoidal function, Gaussian function and so on. In order to avoid local minima, the activation functions are controlled and randomly disturbed every some epochs. The activation functions are automatically optimized for each application. Probability and speed of learning are higher than the conventionals
Keywords :
learning (artificial intelligence); multilayer perceptrons; optimisation; transfer functions; Gaussian function; activation functions; connection weights; learning probability; learning speed; multilayer neural networks; random disturbance; sigmoidal function; simultaneous learning method; Error correction; Learning systems; Multi-layer neural network; Neural networks; Nonhomogeneous media;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687211
