A Deep Neuro-Fuzzy Network for Image Classification
Preprint
Abstract
The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structures having lower generalization capacity. We propose the first end-to-end deep neuro-fuzzy network and investigate its application for image classification. Two new operations are developed based on definitions of Takagi-Sugeno-Kang (TSK) fuzzy model namely fuzzy inference operation and fuzzy pooling operations; stacks of these operations comprise the layers in this network. We evaluate the network on MNIST, CIFAR-10 and CIFAR-100 datasets, finding that the network has a reasonable accuracy in these benchmarks.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Non-stationary Data StreamsIEEE Transactions on Fuzzy Systems, 2019
- A Semi-Supervised CNN With Fuzzy Rough C-Mean for Image ClassificationIEEE Access, 2019
- Semi-supervised deep rule-based approach for image classificationApplied Soft Computing, 2018
- Stacked-Structure-Based Hierarchical Takagi-Sugeno-Kang Fuzzy Classification Through Feature AugmentationIEEE Transactions on Emerging Topics in Computational Intelligence, 2017
- A Pythagorean-Type Fuzzy Deep Denoising Autoencoder for Industrial Accident Early WarningIEEE Transactions on Fuzzy Systems, 2017
- Deep Takagi–Sugeno–Kang Fuzzy Classifier With Shared Linguistic Fuzzy RulesIEEE Transactions on Fuzzy Systems, 2017
- Deep TSK Fuzzy Classifier With Stacked Generalization and Triplely Concise Interpretability Guarantee for Large DataIEEE Transactions on Fuzzy Systems, 2016
- Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep LearningIEEE Transactions on Fuzzy Systems, 2015
- Type-2 fuzzy sets made simpleIEEE Transactions on Fuzzy Systems, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998