...
首页> 外文期刊>Neural processing letters >A L-BFGS Based Learning Algorithm for Complex-Valued Feedforward Neural Networks
【24h】

A L-BFGS Based Learning Algorithm for Complex-Valued Feedforward Neural Networks

机译:基于L-BFGS的复值前馈神经网络学习算法

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

In this paper, a new learning algorithm is proposed for complex-valued feedforward neural networks (CVFNNs). The basic idea of this algorithm is that the descent directions of the cost function with respect to complex-valued parameters are calculated by limited-memory BFGS algorithm and the learning step is determined by Armijo line search method. Since the approximation of Hessian matrix is calculated by utilizing the information of the latest several iterations, the memory efficiency is improved. To keep away from the saturated ranges of activation functions, some gain parameters are adjusted together with weights and biases. Compared with some existing learning algorithms for CVFNNs, the convergence speed is faster and a deeper minima of the cost function can be reached by the developed algorithm. In addition, the effects of initial values of weights and biases on the efficiency and convergence speed of the learning algorithm are analyzed. The performance of the proposed algorithm is evaluated in comparison with some existing classifiers on a variety of benchmark classification problems. Experimental results show that better performance is achieved by our algorithm with relatively compact network structure.
机译:本文针对复值前馈神经网络(CVFNN)提出了一种新的学习算法。该算法的基本思想是,通过有限内存BFGS算法计算成本函数相对于复数值参数的下降方向,并通过Armijo线搜索方法确定学习步骤。由于通过利用最新几次迭代的信息来计算Hessian矩阵的近似值,因此提高了存储效率。为了远离激活函数的饱和范围,需要调整一些增益参数以及权重和偏差。与现有的一些用于CVFNN的学习算法相比,该算法收敛速度更快,并且可以使代价函数的最小值更深。另外,分析了权重和偏差的初始值对学习算法的效率和收敛速度的影响。与一些现有分类器相比,该算法在各种基准分类问题上的性能得到了评估。实验结果表明,我们的算法在网络结构相对紧凑的情况下具有较好的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号