摘要
结合Levenberg-Marquardt算法以及权值直接确定法这两种用于神经网络学习训练的方法,提出了一种带后续迭代、面向双极S(sigmoid)激励函数神经网络的权值与结构确定(weights-and-structure-determination,WASD)方法。该方法与MATLAB软件神经网络工具箱相结合,可以解决传统神经网络普遍存在的学习时间长、网络结构难以确定、学习能力和泛化能力有待提高等不足,同时具有较好的可行性和可操作性。以非线性函数的数据拟合为例,计算机数值实验和对比结果证实了WASD方法确定出最优隐神经元数和最优权值的优越性,最终得到的WASD神经网络具有更为优异的学习性能和泛化性能。
A weights-and-structure-determination（ WASD） algorithm is proposed for the neural network using bipolar sigmoid activation functions together with subsequent iterations,which is the combination of the Levenberg-Marquardt algorithm and the weights-direct-determination method for neural network training. The proposed algorithm,combined with the Neural Network Toolbox of MATLAB software,aims at remedying the common weaknesses of traditional artificial neural networks,such as long-time learning expenditure,difficulty in determining the network structure,and to-be-improved performance of learning and generalization. Meanwhile,the WASD algorithm has good flexibility and operability. Taking data fitting of nonlinear functions for example,numerical experiments and comparison results illustrate the superiority of the WASD algorithm for determining the optimal number and optimal weights of hidden neurons.And the resultant neural network has more excellent performance on learning and generalization.
出处
《中山大学学报（自然科学版）》
CAS
CSCD
北大核心
2016年第4期1-10,共10页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
国家自然科学基金资助项目(61473323)
广州市科技计划资助项目(2014J4100057)
自主系统与网络控制教育部重点实验室开放基金资助项目(2013A07)
大学生创新创业训练计划资助项目(201410558065
201410558069)
关键词
神经网络
权值与结构直接确定
后续迭代
双极S激励函数
数值实验
neural networks
weights-and-structure-determination（WASD） algorithm
subsequent iterations
bipolar sigmoid activation functions
numerical experiments
