arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.03202cs.LGstat.ML
收藏

基于可解释神经网络的分类器

Interpretable Neural Networks based classifiers for categorical inputs

École Polytechnique Féderale de Lausanne (EPFL)(洛桑联邦理工学院)

Stefano Zamuner, Paolo De Los Rios

摘要:

由于神经网络在人类敏感应用中的广泛使用,其可解释性正在成为机器学习中越来越重要的主题。在这项工作中,我们介绍了一种简单的方法来解释的输出功能的神经网络分类器,作为输入的分类变量。通过利用一个神经网络分类器和一个物理能量模型之间的映射,我们表明,在这些情况下,网络的每一层,特别是logits层,可以扩展为一个项的总和,占每个输入模式的分类的贡献。例如,在第一阶,扩展仅考虑输入特征和输出之间的线性关系,而在第二阶,还考虑了输入特征之间的成对依赖关系。每个模式的贡献的分析,经过适当的规范变换,在两种情况下,该方法的有效性可以理解。

英文摘要:

Because of the pervasive usage of Neural Networks in human sensitive applications, their interpretability is becoming an increasingly important topic in machine learning. In this work we introduce a simple way to interpret the output function of a neural network classifier that take as input categorical variables. By exploiting a mapping between a neural network classifier and a physical energy model, we show that in these cases each layer of the network, and the logits layer in particular, can be expanded as a sum of terms that account for the contribution to the classification of each input pattern. For instance, at the first order, the expansion considers just the linear relation between input features and output while at the second order pairwise dependencies between input features are also accounted for. The analysis of the contributions of each pattern, after an appropriate gauge transformation, is presented in two cases where the effectiveness of the method can be appreciated.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑