一种通过反馈提高神经网络学习性能的新算法

为了有效提高前向神经网络的学习性能，需要从一个新的角度考虑神经网络的学习训练．基于此，提出了一种基于结果反馈的新算法——FBBP算法．将神经网络输入调整与通常的权值调整的反向传播算法结合起来，通过调整权值和输入矢量值的双重作用来最小化神经网络的误差函数．并通过几个函数逼近和模式分类问题的实例仿真，将FBBP算法与加动量项BP算法、最新的一种加快收敛的权值更新的算法进行了比较，来验证所提出的算法的有效性．实验结果表明，所提出的算法具有训练速度快和泛化能力高的双重优点，是一种非常有效的学习方法．

A New Algorithm to Improve the Learning Performance of Neural Network Through Result-Feedback

The combination of input vector tuning with traditional weight tuning of back propagation algorithm results in a new algorithm on the basis of result feedback (FBBP) This FBBP based algorithm is an inner and outer layer learning method in which weight value renewing plays the dominating role with the assistance of input renewing It minimizes the error function of neural network through the dual functioning of weight value and input vector value tuning In the process neural network learning and training are estimated from an angle of result feedback along with the objective to effectively improve the learning performance of feed forward neural network Quite a few simulation experiments serve to make comparisons between the FBBP algorithm, the BP algorithm with momentum term, and a recently published algorithm that used weight updating method to speed up convergence Experiment results are discussed in detail The results show that the new algorithm has the dual merits of quick training speed and good generalization capability It proves to be a very effective learning method