| 引用本文: | 张少仲,李龙锁,任世军,蒋波,白英,张维石.填充函数法改进的BP网络SPDS算法[J].哈尔滨工业大学学报,2013,45(7):126.DOI:10.11918/j.issn.0367-6234.2013.07.023 |
| ZHANG Shaozhong,LI Longsuo,REN Shijun,JIANG Bo,BAI Ying,ZHANG Weishi.Improved SPDS algorithm in BP network based on filled function method[J].Journal of Harbin Institute of Technology,2013,45(7):126.DOI:10.11918/j.issn.0367-6234.2013.07.023 |
|
| 摘要: |
| BP网络的训练算法的一个普遍问题是易陷入局部极小．为了解决SPDS算法的这个问题,针对其特点设计了一组新填充函数．通过对该填充函数的分析,证明了用它代替目标函数进行搜索的等价性,并据此改进了SPDS算法．算法的仿真试验证明: 当SPDS算法陷入局部极小点时,用设计的填充函数代替目标函数,从而使算法不受局部极小问题的羁绊,可以快速收敛到全局极小点． |
| 关键词: BP网络 填充函数法 局部极小问题 |
| DOI：10.11918/j.issn.0367-6234.2013.07.023 |
| 分类号: |
| 基金项目:国家自然科学基金资助项目(61173034). |
|
| Improved SPDS algorithm in BP network based on filled function method |
|
ZHANG Shaozhong1, LI Longsuo2, REN Shijun2, JIANG Bo1, BAI Ying1, ZHANG Weishi1
|
|
(1.Information School, Dalian Maritime University, 116026 Dalian, China; 2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China)
|
| Abstract: |
| To solve the problem that the BP network training algorithm is easy to fall into local minimal point, this paper designs a set of new filled function in view of its characteristic, which can be used to replace the objective function for search and improve the SPDS algorithm. The algorithm simulation test proves that, when the SPDS algorithm falls into local minimum point, the use of the filled function instead of objective function makes the algorithm avoid the fetters of minimum problem, and accelerates convergence to the global minimum point. |
| Key words: BP network Filled function method Local minimum problem
|
