首页> 外文会议>IEEE International Conference on Neural Networks >Square root learning in batch mode BP for classification problems
【24h】

Square root learning in batch mode BP for classification problems

机译:批量模式BP的平方根学习进行分类问题

获取原文

摘要

An algorithm is proposed to increase the learning speed of the standard batch mode BP algorithm for a multilayer perceptron in pattern classification problems. In many problems, the standard batch mode BP suffers from an initial slow learning period. The purpose of the proposed algorithm is to analyze the initial slow learning and to make neural networks converge fast to a local minimum. The key ideas of the proposed algorithm are to use a normalized objective function, to normalize the gradient of the batch mode BP, and to change the learning rate based on the square root of the current gradient norm. The momentum parameter for each weight is also changed according to the normalized gradient. Simulation results demonstrate that the proposed algorithm shortens the initial slow learning period of the batch mode BP and gives a better performance than the online mode BP.
机译:提出了一种算法,以提高模式分类问题中多层批量批量模具BP算法的学习速度。在许多问题中,标准批量模式BP遭受初始慢速学习期。所提出的算法的目的是分析初始慢速学习,并使神经网络迅速收敛到局部最小值。所提出的算法的关键思想是使用归一化的目标函数,以将批量模式BP的梯度标准化,并基于电流梯度范数的平方根来改变学习率。根据归一化梯度也改变了每种重量的动量参数。仿真结果表明,所提出的算法缩短了批量模式BP的初始慢速学习期,并提供比在线模式BP更好的性能。

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