COMPARISON STUDY OF SENSITIVITY DEFINITIONS OF NEURAL NETWORKS

摘要：

This paper compares the sensitivity definitions of neural networks output to input and weight perturbations.Based on the essence of the sensitivity definitions, the authors classify these sensitivity definitions into 3 categories: Noise-to- Signal Ratio, Geometrical property of derivative, Angle perturbation in Geometry space.The characteristics of these 3 categories of sensitivity definition are discussed respectively, It is sensible to classify these sensitivity definitions based on the essence of them for researchers can find other new sensitivity definitions of neural networks.

关键词： Sensitivity definition Categories Neural networks Comparison

作者: CHUN-GUO LI HAI-FENG LI AI-KE YAO NING XU

作者单位: Machine Learning Center, Faculty of Mathematics and Computer Science, Hebei University, Baoding 0710 Department of educational administration, Hebei University, Baoding 071002, China Department of State Assets Management, HeBei Software Institute, Baoding, 071000, China Industrial and Commercial College, Hebei University, Baoding, 071002, China

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 3472-3477

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）