DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System
Authors:
- Mojtaba YeganejouMYMojtaba Yeganejou
- Kimia HonariKHKimia Honari
- Ryan KluzinskiRKRyan Kluzinski
- Scott DickSDScott Dick
- Michael LipsettMLMichael Lipsett
- James MillerJMJames Miller
Preprint
Abstract
A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset.Keywords
All Related Versions
This publication has 53 references indexed in Scilit:
- DARPA's explainableAI(XAI) program: A retrospectiveApplied AI Letters, 2021
- Generating visual explanations with natural languageApplied AI Letters, 2021
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- Semi-supervised deep rule-based approach for image classificationApplied Soft Computing, 2018
- Fuzzy qualitative deep compression networkNeurocomputing, 2017
- Deep Convolutional Neural Networks for Large-scale Speech TasksNeural Networks, 2015
- Interpretability of linguistic fuzzy rule-based systems: An overview of interpretability measuresInformation Sciences, 2011
- The Benefits of Interactions with Physically Present Robots over Video-Displayed AgentsInternational Journal of Social Robotics, 2010
- Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learningInternational Journal of Approximate Reasoning, 2007
- Similarity relations, fuzzy partitions, and fuzzy orderingsFuzzy Sets and Systems, 1991