Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning

By Guido Bologna, Yoichi Hayashi. 2017

92 citations recorded by the source corpus.

Abstract Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets we performed rule extraction from ensembles of Discretized Interpretable Multi Layer Perceptrons (DIMLP), and DIMLPs trained by deep learning. The results obtained on the Thyroid dataset and the Wisconsin Breast Cancer dataset show that the predictive accuracy of the extracted rules compare very favorably with respect to state of the art results. Finally, in the last classification problem on digit recognition, generated rules from the MNIST dataset can be viewed as discriminatory features in particular digit areas. Qualitatively, with respect to rule complexity in terms of number of generated rules and number of antecedents per rule, deep DIMLPs and DIMLPs trained by arcing give similar results on a binary classification problem involving digits 5 and 8. On the whole MNIST problem we showed that it is possible to determine the feature detectors created by neural networks and also that the complexity of the extracted rulesets can be well balanced between accuracy and interpretability.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

What do we need to build explainable AI systems for the medical domain? (2017, neutral): “Often the best-performing methods (e.g., deep learning) are the least transparent, and the ones providing a clear explanation (e.g., decision trees) are less accurate (Bologna and Hayashi, 2017).”
Key challenges for delivering clinical impact with artificial intelligence (2019, background): “A key current limitation of deep learning models is that they have no explicit declarative knowledge representation, leading to considerable difficulty in generating the required explanation structures [90].”
Causability and explainability of artificial intelligence in medicine (2019, methodology): “Often the best-performing methods such as DL are the least transparent, and the ones providing a clear explanation (e.g., decision trees) are less accurate (Bologna & Hayashi, 2017).”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Discretized Interpretable Multi-Layer Perceptrons (DIMLP) [139, 240, 241, 132] returns”
Measuring the Quality of Explanations: The System Causability Scale (SCS) (2019, unknown): “full potential [12].”