Paper Info
Title
Interpretable Machine Learning: Convolutional Neural Networks with RBF Fuzzy Logic Classification Rules
Abstract
A convolutional neural network (CNN) learning structure is proposed, with added interpretability-oriented layers, in the form of Fuzzy Logic-based rules. This is achieved by creating a classification layer based on a Neural-Fuzzy classifier, and integrating it into the overall learning mechanism within the deep learning structure. Using this new structure, one could extract linguistic Fuzzy Logic-based rules from the deep learning structure directly, which enhances the interpretability of the overall system. The classification layer is realised via a Radial Basis Function (RBF) Neural-Network, that is a direct equivalent of a class of Fuzzy Logic-based systems. In this work, the development of the RBF neural-fuzzy system and its integration into the deep-learning CNN is presented. The proposed hybrid CNN RBF-NF structure can from a fundamental building block, towards building more complex deep-learning structures with Fuzzy Logic-based interpretability. Using simulation results on a benchmark data-driven modelling and classification problem (labelled handwriting digits, MNIST 70000 samples) we show that the proposed learning structure maintains a good level of forecasting/prediction accuracy (> 96% on unseen data) compared to state-of-the-art CNN deep learning structures, while providing linguistic interpretability to the classification layer.
Year
DOI
Venue
2018
10.1109/IS.2018.8710470
2018 International Conference on Intelligent Systems (IS)
Keywords
Field
DocType
Fuzzy Logic,Deep Learning,Convolutional Neural Networks
Interpretability,Radial basis function,MNIST database,Handwriting,Convolutional neural network,Computer science,Fuzzy logic,Artificial intelligence,Deep learning,Classifier (linguistics)
Conference
ISSN
ISBN
Citations 
1541-1672
978-1-5386-7098-9
0
PageRank 
References 
Authors
0.34
10
2
Name
Order
Citations
PageRank
Zhen Xi100.34
George Panoutsos2577.59