Title :
An adaptive activation function for multilayer feedforward neural networks
Author :
Yu, Chien-Cheng ; Tang, YunChing ; Liu, Bin-Da
Abstract :
The aim of this paper is to propose a new adaptive activation function for multilayer feedforward neural networks. Based upon the backpropagation (BP) algorithm, an effective learning method is derived to adjust the free parameters in the activation function as well as the connected weights between neurons. Its performance is demonstrated by the N-parity and two-spiral problems. The simulation results showed that the proposed method is more suitable to the pattern classification problems and its learning speed is much faster than that of traditional networks with fixed activation function.
Keywords :
backpropagation; feedforward neural nets; multilayer perceptrons; pattern classification; transfer functions; BP algorithm; N-parity problem; adaptive activation function; backpropagation algorithm; free parameter adjustment; learning speed; multilayer feedforward neural networks; neuron connected weights; pattern classification; performance; two-spiral problem; Adaptive algorithm; Artificial neural networks; Councils; Feedforward neural networks; Information processing; Learning systems; Multi-layer neural network; Neural networks; Neurons; Pattern recognition;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1181357
