...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural computation >Initializing Weights of a Multilayer Perceptron Network by Using the Orthogonal Least Squares Algorithm
【24h】

Initializing Weights of a Multilayer Perceptron Network by Using the Orthogonal Least Squares Algorithm

机译：正交最小二乘算法初始化多层感知器网络的权重

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Usually the training of a multilayer perceptron network starts by initializing the network weights with small random values, and then the weight adjustment is carried out by using an iterative gradient descent-based optimization routine called backpropagation training. If the random initial weights happen to be far from a good solution or they are near a poor local optimum, the training will take a lot of time since many iteration steps are required. Furthermore, it is very possible that the network will not converge to an adequate solution at all. On the other hand, if the initial weights are close to a good solution the training will be much faster and the possibility of obtaining adequate convergence increases. In this paper a new method for initializing the weights is presented. The method is based on the orthogonal least squares algorithm. The simulation results obtained with the proposed initialization method show a considerable improvement in training compared to the randomly initialized networks. In light of practical experiments, the proposed method has proven to be fast and useful for initializing the network weights.
机译：通常，多层感知器网络的训练是通过初始化具有较小随机值的网络权重开始的，然后使用称为迭代传播训练的基于迭代梯度下降的优化例程来进行权重调整。如果随机初始权重碰巧不是很好的解决方案，或者它们接近较差的局部最优值，则由于需要许多迭代步骤，因此训练将花费大量时间。此外，网络极有可能根本无法收敛到适当的解决方案。另一方面，如果初始权重接近一个好的解决方案，则训练将更快，并且获得足够收敛的可能性也会增加。本文提出了一种初始化权重的新方法。该方法基于正交最小二乘算法。与随机初始化的网络相比，使用建议的初始化方法获得的仿真结果显示出训练方面的显着改进。根据实际实验，该方法已被证明是快速有效的初始化网络权重。

著录项

  • 来源
    《Neural computation》 |1995年第5期|982-999|共18页
  • 作者

    Lehtokangas M; Saarinen J; Kaski K; Huuhtanen P;

  • 作者单位

    Tampere University of Technology, Microelectronics Laboratory, P.O. Box 692, FIN-33101 Tampere, Finland;

  • 收录信息 美国《科学引文索引》(SCI);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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