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 2003.12317cs.LGstat.ML
收藏

基于Copula的神经网络可视化技术

A copula-based visualization technique for a neural network

NEC Corporation(日本电气股份有限公司);National Institute of Advanced Industrial Science and Technology(产业技术综合研究所)

Yusuke Kubo, Yuto Komori, Toyonobu Okuyama, Hiroshi Tokieda

摘要:

机器学习的可解释性被定义为人类能够理解决策原因的程度。然而,神经网络由于其决策过程中的模糊性而不被认为是可解释的。因此,在这项研究中,我们提出了一种新的算法,揭示了哪些特征值的训练神经网络认为重要的,哪些路径主要是在决策过程中跟踪。在该算法中,定义了由神经网络层之间的相关系数估计的得分,该相关系数可以通过应用对copula的概念来计算。我们比较了估计的分数与随机森林的特征重要性值,这有时被认为是一个高度可解释的算法,在实验中,并确认结果是一致的。该算法提出了一种用于压缩神经网络及其参数调整的方法,因为该算法识别有助于分类或预测结果的路径。

英文摘要:

Interpretability of machine learning is defined as the extent to which humans can comprehend the reason of a decision. However, a neural network is not considered interpretable due to the ambiguity in its decision-making process. Therefore, in this study, we propose a new algorithm that reveals which feature values the trained neural network considers important and which paths are mainly traced in the process of decision-making. In the proposed algorithm, the score estimated by the correlation coefficients between the neural network layers that can be calculated by applying the concept of a pair copula was defined. We compared the estimated score with the feature importance values of Random Forest, which is sometimes regarded as a highly interpretable algorithm, in the experiment and confirmed that the results were consistent with each other. This algorithm suggests an approach for compressing a neural network and its parameter tuning because the algorithm identifies the paths that contribute to the classification or prediction results.

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。

↑