首页> 外文会议>2001 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001. Proceedings, 2001 >A high order Boltzmann machine configuration for transfer sequencesearches in decomposed state machines
【24h】

A high order Boltzmann machine configuration for transfer sequencesearches in decomposed state machines

机译:用于分解状态机中传输序列搜索的高阶玻尔兹曼机配置

获取原文

摘要

Summary form only given, as follows. A neural network architecturein the form of a high-order Boltzmann machine is proposed for thetransfer sequence search of a decomposed sequential machine. Thetransfer sequence for each component machine can be found using asecond-order Boltzmann machine, but the dependencies between componentmachines require high-order connections. The Boltzmann machineconfiguration as a constraint satisfaction network for a sequentialmachine structure is defined. The global and the local energy terms forthe overall architecture are defined based on the component machinestate tables and the state transition dependencies between machines. Theapplication of the proposed architecture to a sample problem isdemonstrated by using a fourth-order Boltzmann machine for the transfersequence search in a serially decomposed sequential machine
机译:仅给出摘要表格,如下。提出了一种高阶玻尔兹曼机形式的神经网络体系结构,用于分解序列机的传输序列搜索。可以使用二阶Boltzmann机器找到每个组件机器的传输顺序,但是组件机器之间的依存关系需要高阶连接。定义了Boltzmann机器配置作为顺序机器结构的约束满足网络。基于组件的机器状态表和机器之间的状态转换依存关系来定义整个体系结构的全局和局部能量项。通过使用四阶Boltzmann机器在串行分解的序列机器中进行转移序列搜索,证明了所提出的体系结构在样本问题上的应用

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