期刊
NEUROCOMPUTING
卷 99, 期 -, 页码 390-398出版社
ELSEVIER
DOI: 10.1016/j.neucom.2012.07.020
关键词
Sensitivity; Multilayer Perceptron; Neural network
资金
- National Natural Science Foundation of China [60571048, 60971088]
- Research Innovation Program for College Postgraduate in Jiangsu Province [CX09B_157Z]
- Hohai University [2010B19214]
The sensitivity of a neural network's output to its inputs' perturbations is an important measure for evaluating the network's performance. To make the sensitivity be a practical tool for designing and implementing Multi layer Perceptrons (MLPs), this paper proposes a general approach to quantify the sensitivity of MLPs. The sensitivity is defined as the mathematical expectation of absolute output deviations due to input perturbations with respect to all possible inputs, and computed following a bottom-up way, in which the sensitivity of a neuron is first considered and then is that of the entire network. The main contribution of the approach is that it requests a weak assumption on the input, that is, input elements need only to be independent of each other without being restricted to have a certain type of distribution and thus is more applicable to real applications. Some experimental results on artificial datasets and real datasets demonstrate the proposed approach is highly accurate. (C) 2012 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据