On fine-tuning of Autoencoders for Fuzzy rule classifiers

TL;DR

This paper introduces a novel framework combining autoencoders with fuzzy rule classifiers, incorporating expert knowledge and four fine-tuning strategies, achieving state-of-the-art accuracy on benchmark datasets.

Contribution

It presents a new method integrating autoencoders into FRCs with four innovative fine-tuning strategies for enhanced performance.

Findings

Achieved state-of-the-art accuracy on five benchmark datasets.

Demonstrated improved classification and rule reduction performance.

Validated robustness through 10-fold cross-validation.

Abstract

Recent discoveries in Deep Neural Networks are allowing researchers to tackle some very complex problems such as image classification and audio classification, with improved theoretical and empirical justifications. This paper presents a novel scheme to incorporate the use of autoencoders in Fuzzy rule classifiers (FRC). Autoencoders when stacked can learn the complex non-linear relationships amongst data, and the proposed framework built towards FRC can allow users to input expert knowledge to the system. This paper further introduces four novel fine-tuning strategies for autoencoders to improve the FRC's classification and rule reduction performance. The proposed framework has been tested across five real-world benchmark datasets. Elaborate comparisons with over 15 previous studies, and across 10-fold cross validation performance, suggest that the proposed methods are capable of building FRCs which can provide state of the art accuracies.