A Hybrid Training Algorithm for Feedforward Neural Networks |
| |
Authors: | Mounir Ben Nasr Mohamed Chtourou |
| |
Affiliation: | (1) Department of Electrical Engineering, Research Unit on Intelligent Control, Design and Optimization of Complex Systems (ICOS), ENIS, BPW, 3038 Sfax, Tunisia |
| |
Abstract: | Feedforward neural networks (FNN) have been proposed to solve complex problems in pattern recognition, classification and function approximation. Despite the general success of learning methods for FNN, such as the backpropagation (BP) algorithm, second-order algorithms, long learning time for convergence remains a problem to be overcome. In this paper, we propose a new hybrid algorithm for a FNN that combines unsupervised training for the hidden neurons (Kohonen algorithm) and supervised training for the output neurons (gradient descent method). Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods. |
| |
Keywords: | feedforward neural network gradient descent method supervised and unsupervised learning self-organizing map hybrid training |
本文献已被 SpringerLink 等数据库收录! |
|