Avoiding Poor Local Minima in Training Multilayer Perceptrons

摘要：

A training method is reported that adoptively selects a risk-averting error criterion to suit the function under approximation and the noise statistics of the training data so as to include fine features of the function and its segments under-represented in the training data.A companion paper also presented at ICONIP01 proves that the method has the ability to avoid poor local minima of the selected criterion. Numerical examples given illustrate the efficacy of this training method.

作者: James Ting-Ho Lo Devasis Bassu

作者单位: Department of Mathematics and Statistics University of Maryland Baltimore County Baltimore, MD 21228, U.S.A.

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1365-1370

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）