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 2202.00345cs.LG
收藏

探索DNN中的分层决策

Exploring layerwise decision making in DNNs

Faculty of Engineering, North-West University(西北大学工程学院);North-West University(西北大学)

Coenraad Mouton, Marelie H. Davel

摘要:

虽然深度神经网络(DNN)已经成为许多机器学习任务的标准架构,但其内部决策过程和一般可解释性仍然知之甚少。相反,普通的决策树很容易解释,理论上也很容易理解。我们表明,通过将节点的离散样本激活值编码为二进制表示,我们能够提取一棵决策树,解释ReLU激活的多层感知器(MLP)中每一层的分类过程。然后,我们将这些决策树与现有的特征属性技术相结合,以产生模型的每一层的解释。最后,我们提供了一个分析所产生的解释,二进制编码的行为,以及这些如何与样本分组过程中创建的神经网络的训练过程中。

英文摘要:

While deep neural networks (DNNs) have become a standard architecture for many machine learning tasks, their internal decision-making process and general interpretability is still poorly understood. Conversely, common decision trees are easily interpretable and theoretically well understood. We show that by encoding the discrete sample activation values of nodes as a binary representation, we are able to extract a decision tree explaining the classification procedure of each layer in a ReLU-activated multilayer perceptron (MLP). We then combine these decision trees with existing feature attribution techniques in order to produce an interpretation of each layer of a model. Finally, we provide an analysis of the generated interpretations, the behaviour of the binary encodings and how these relate to sample groupings created during the training process of the neural network.

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。

↑