当前位置: X-MOL 学术J. Big Data › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Novel sensitivity method for evaluating the first derivative of the feed-forward neural network outputs
Journal of Big Data ( IF 8.6 ) Pub Date : 2021-06-10 , DOI: 10.1186/s40537-021-00480-4
Ravi Kiran , Dayakar L. Naik

Evaluating the exact first derivative of a feedforward neural network (FFNN) output with respect to the input feature is pivotal for performing the sensitivity analysis of the trained neural network with respect to the inputs. In this paper, a novel method is presented that computes the analytical quality first derivative of a trained feedforward neural network output with respect to the input features without the need for backpropagation. To this end, the complex step derivative approximation is illustrated, and its implementation in the framework of the feedforward neural network is described. Artificial datasets are generated, and the efficacy of the proposed method for both regression and classification tasks is demonstrated. The results obtained for the regression task indicated that the proposed method is capable of obtaining analytical quality derivatives, and in the case of the classification task, the least relevant features could be identified.



中文翻译:

评估前馈神经网络输出的一阶导数的新灵敏度方法

评估前馈神经网络 (FFNN) 输出相对于输入特征的精确一阶导数对于执行已训练神经网络相对于输入的敏感性分析至关重要。在本文中,提出了一种新方法,该方法无需反向传播即可计算训练过的前馈神经网络输出相对于输入特征的分析质量一阶导数。为此,说明了复阶导数近似,并描述了它在前馈神经网络框架中的实现。生成人工数据集,并证明了所提出的方法对回归和分类任务的有效性。

更新日期:2021-06-11
down
wechat
bug