Decision Tree Extraction using Trained Neural Network

This paper introduces an algorithm for the extraction of rules from trained neural network. One of the main disadvantages of neural networks is their presumed complexity and people's inability to fully comprehend their underlying logic. Their black box nature deems them useless in cases where the process of classification is important and must be presented in an observable and understandable way. The described algorithm extracts rules from a trained neural network and presents them in a form easily interpretable to humans. The paper demonstrates different approaches of rule extraction. Extracted rules explain and illustrate the network's decision-making process. Rules can also be observed in the form of a tree. The presented algorithm generates rules by changing the input data and classifying them using the Reverse Engineering approach. After processing the data, the algorithm can use different approaches for creating the rules.