首页> 外文学位 >A learning automaton approach to trajectory learning and control system design using dynamic recurrent neural networks.
【24h】

A learning automaton approach to trajectory learning and control system design using dynamic recurrent neural networks.

机译:一种使用动态递归神经网络进行轨迹学习和控制系统设计的学习自动机方法。

获取原文
获取原文并翻译 | 示例

摘要

This thesis presents a method for the training of dynamic, recurrent neural networks to generate continuous-time trajectories. In the past, most methods for this type of training were based on gradient descent methods and were deterministic. The method presented here is stochastic in nature. The problem of local minima is addressed by adding the enhancement of incremental learning to the learning automaton; i.e., small learning goals are used to train the neural network from its initialized state to its final parameters for the desired response. The method is applied to the learning of a benchmark continuous-time trajectory–the circle. Then the learning automaton approach is applied to stabilization and tracking problems for linear and nonlinear plant models, using either state or output feedback as needed.
机译:本文提出了一种训练动态递归神经网络以生成连续时间轨迹的方法。过去,大多数此类训练方法都是基于梯度下降法并且是确定性的。这里介绍的方法本质上是随机的。通过在学习自动机中增加增量学习来解决局部极小值的问题。即,小的学习目标用于将神经网络从其初始状态训练到最终参数以获得所需的响应。该方法适用于基准连续时间轨迹(圆)的学习。然后将学习自动机方法应用于线性和非线性工厂模型的稳定和跟踪问题,并根据需要使用状态或输出反馈。

著录项

  • 作者

    Condarcure, Thomas A.;

  • 作者单位

    The University of Arizona.;

  • 授予单位 The University of Arizona.;
  • 学科 Engineering Electronics and Electrical.;Computer Science.;Artificial Intelligence.
  • 学位 M.S.
  • 年度 1993
  • 页码 126 p.
  • 总页数 126
  • 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