论文标题
使用新颖的扩展Garson算法来解释基于信念网络的自动编码器
Explainable Deep Belief Network based Auto encoder using novel Extended Garson Algorithm
论文作者
论文摘要
机器学习中最困难的任务是解释训练有素的浅神经网络。深度神经网络（DNNS）为大量任务提供了令人印象深刻的结果，但是通常不清楚这种训练有素的深神经网络如何做出决策。提供特征重要性是浅层神经网络中最重要，最受欢迎的解释技术。在本文中，我们开发了一种算法，扩展了Garson算法的思想，以解释基于信念网络的自动编码器（DBNA）。它用于确定DBN中每个输入特征的贡献。它可用于具有许多隐藏层的任何神经网络。该方法的有效性在分类和从文献中获取的回归数据集进行了测试。将此方法确定的重要特征与Wald Chi Square（\ c {hi} 2）获得的特征进行了比较。对于4个分类数据集中的2个和5个回归数据集中的2个，我们提出的方法可以识别出更好质量的特征，从而导致统计上更重要的结果与Wald \ c {hi} 2。
The most difficult task in machine learning is to interpret trained shallow neural networks. Deep neural networks (DNNs) provide impressive results on a larger number of tasks, but it is generally still unclear how decisions are made by such a trained deep neural network. Providing feature importance is the most important and popular interpretation technique used in shallow and deep neural networks. In this paper, we develop an algorithm extending the idea of Garson Algorithm to explain Deep Belief Network based Auto-encoder (DBNA). It is used to determine the contribution of each input feature in the DBN. It can be used for any kind of neural network with many hidden layers. The effectiveness of this method is tested on both classification and regression datasets taken from literature. Important features identified by this method are compared against those obtained by Wald chi square (\c{hi}2). For 2 out of 4 classification datasets and 2 out of 5 regression datasets, our proposed methodology resulted in the identification of better-quality features leading to statistically more significant results vis-à-vis Wald \c{hi}2.
