Affiliation:
1. Department of Computer Science, University of Applied Sciences and Arts of Western Switzerland, Rue de la Prairie 4, 1202 Geneva, Switzerland
Abstract
The explainability of connectionist models is nowadays an ongoing research issue. Before the advent of deep learning, propositional rules were generated from Multi Layer Perceptrons (MLPs) to explain how they classify data. This type of explanation technique is much less prevalent with ensembles of MLPs and deep models, such as Convolutional Neural Networks (CNNs). Our main contribution is the transfer of CNN feature maps to ensembles of DIMLP networks, which are translatable into propositional rules. We carried out three series of experiments; in the first, we applied DIMLP ensembles to a Covid dataset related to diagnosis from symptoms to show that the generated propositional rules provided intuitive explanations of DIMLP classifications. Then, our purpose was to compare rule extraction from DIMLP ensembles to other techniques using cross-validation. On four classification problems with over 10,000 samples, the rules we extracted provided the highest average predictive accuracy and fidelity. Finally, for the melanoma diagnostic problem, the average predictive accuracy of CNNs was 84.5% and the average fidelity of the top-level generated rules was 95.5%. The propositional rules generated from the CNNs were mapped at the input layer by squares in which the relevant data for the classifications resided. These squares represented regions of attention determining the final classification, with the rules providing logical reasoning.
Funder
Swiss State Secretariat for Education, Research and Innovation
Reference50 articles.
1. Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models;Sudars;Comput. Assist. Methods Eng. Sci.,2022
2. Rudin, C. (2018). Please stop explaining black box models for high stakes decisions. arXiv.
3. Survey and critique of techniques for extracting rules from trained artificial neural networks;Andrews;Knowl.-Based Syst.,1995
4. Diederich, J. (2008). Rule Extraction from Support Vector Machines, Springer Science and Business Media.
5. Bagging predictors;Breiman;Mach. Learn.,1996