On the one hand, artificial neural networks (ANNs) are commonly labelled as black-boxes, lacking interpretability; an issue that hinders human understanding of ANNs' behaviors. A need exists to generate a meaningful sequential logic of the ANN for interpreting a production process of a specific output. On the other hand, decision trees exhibit better interpretability and expressive power due to their representation language and the existence of efficient algorithms to transform the trees into rules. However, growing a decision tree based on the available data could produce larger than necessary trees or trees that do not generalise well. In this paper, we introduce two novel multivariate decision tree (MDT) algorithms for rule extraction from ANNs: an Exact-Convertible Decision Tree (EC-DT) and an Extended C-Net algorithm. They both transform a neural network with Rectified Linear Unit activation functions into a representative tree, which can further be used to extract multivariate rules for reasoning. While the EC-DT translates an ANN in a layer-wise manner to represent exactly the decision boundaries implicitly learned by the hidden layers of the network, the Extended C-Net combines the decompositional approach from EC-DT with a C5 tree learning algorithm to form decision rules. The results suggest that while EC-DT is superior in preserving the structure and the fidelity of ANN, Extended C-Net generates the most compact and highly effective trees from ANN. Both proposed MDT algorithms generate rules including combinations of multiple attributes for precise interpretations for decision-making.
翻译:一方面,人为神经网络(ANNS)通常被贴上黑盒子标签,缺乏解释性;这是一个阻碍人类理解ANNS行为的问题;需要生成ANN的有意义的连续逻辑来解释特定产出的生产过程。另一方面,决策树由于其代表语言和将树木转化为规则的有效算法,而将解释性和表达力表现得更好。然而,根据现有数据种植决策树可能产生大于必要树木或树木,但不能概括化。在本文中,我们为从ANNNS提取规则引入了两种新的多变量决定树(MDT)新颖的多变量(MDT)算法:一个可解释性决定树(EC-DT)和扩展的CNet算法。它们将带有校正线性线性单位激活功能的线性网络转换成具有代表性的树体网络。EC-DTD可以以层次化的方式翻译ANNE(MT),同时将EC-NF规则的精度解释与EC-Q-DMDM(C-DG)的精度解释与EC-Salalal-Destryalalalal IM 的C-dealalalal-Lisal 和EC-C-C-DMT-DMT-L-L-DMT-DMDMT-L-L-S-S-Lisal-Lisal-LM-S-S-S-S-S-S-S-S-S-S-S-DMDMDM-S-S-S-S-S-DMDM-C-C-DMDMDF)相结合。