Singularities in the parameter identification of nonlinear dynamic systems

摘要：

　　Singularity and plateau phenomenon are ubiquitous in the learning process of neural networks.As is known,in the singular regions,the Fisher information matrix degenerates and its inverse G-1 does not exist.The Cramér-Rao theorem is no longer valid at the singular regions.What we want to know is whether the singularities exist in the learning process of the other nonlinear systems and how they affect the learning dynamics.In this paper,for a typical nonlinear system,we give an explicit expression of the Fisher information matrix and find that in the parameter identification of this nonlinear systems,the singularities exist and the plateau phenomenon arises in the learning curve.A simulation example is provided to demonstrate the theoretical analysis in the section 3.

关键词： Nonlinear system Parameter identification Singularity Fisher information matrix

作者: ZHAO Junsheng WEI Haikun GUO Weili ZHANG Kanjian

作者单位: Key Laboratory of Measurement and Control of CSE,Ministry of Education,School of Automation,Southeas Key Laboratory of Measurement and Control of CSE,Ministry of Education,School of Automation,Southeas

会议类型: 国际会议

会议名称: The 33th Chinese Control Conference第33届中国控制会议

会议地点: 南京

会议语种:英文

页码: 6610-6614

在线出版日期: 2014-07-28（万方平台首次上网日期，不代表论文的发表时间）