A synergetic training algorithm based on potential energy function optimized

摘要：

The traditional training method of synergetic neural network is to calculate prototype vector first, then adjoint vector is figured out from prototype vector according to certain rules, the whole course is slowly. The studying of potential energy function dynamics process can train prototype vector and adjoint vector meanwhile. The optimization approach is introduced to synergetic dynamics evolution process, using the memory gradient algorithm instead of the steepest gradient algorithm to optimize the potential energy function, experiment result on cell images recognition shows that the new algorithm can effectively search the prototype vector and adjoint vector meanwhile, and excellent, correct and fast recognition result show the new algorithm is more available than traditional training method.

关键词： Synergetic neural network(SNN) optimization method potential energy function memory gradient method

作者: Zou Gang Ao Yong-Hong Yao Wei Sun Ji-Xiang

作者单位: Information Center ,National university ofDefence TechnologyChangSha, China Department Institute of electronic engineeringNational university of Defence TechnologyChangSha, Chi Department Institute of electronic engineering National university of Defence Technology ChangSha, C

会议类型: 国际会议

会议名称: 2010 2nd IEEE International Conference on Information Management and Engineering(2010年IEEE第二届信息管理与工程国际会议 IEEE ICIME 2010)

会议地点: 成都

会议语种:英文

页码: 1-5

在线出版日期: 2010-04-16（万方平台首次上网日期，不代表论文的发表时间）