一种前馈神经网络的快速学习算法

A Novel Fast Learning Algorithm for Feedforward Neural Network

本文提出一种前馈神经网络的快速学习算法。与传统的BP方法相比,本算法有两个改进之处,一是同时将网络的非线性输出误差与线性输出误差作为待优化的目标函数,二是改进了学习过程中误差的反向传播因子。仿真结果表明,使用本文的算法训练前馈神经网络,计算复杂度略高于BP算法,但学习速度却有显著的提高。

In this paper, a novel fast learning algorithm for multilayered feedforward neural network is introduced. As compared to the conventional BP algorithm, the first improvement of this algorithm is the minimization of a combined error criterion based on the sum of nonlinear and linear quadratic errors of the output neurons, the other is the using of a modified error backpropagation factor in the learning process. The simulation results indicate that the learning speed of this algorithm exceeds that of the conventional BP algorithm evidently, as well as only a little increase in the computational complexity.