4.8 Article

Fast Training of Adversarial Deep Fuzzy Classifier by Downsizing Fuzzy Rules With Gradient Guided Learning

Journal

IEEE TRANSACTIONS ON FUZZY SYSTEMS
Volume 30, Issue 6, Pages 1967-1980

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TFUZZ.2021.3072498

Keywords

Training; Classification algorithms; Takagi-Sugeno model; Neural networks; Fuzzy sets; Computer science; Benchmark testing; Adversarial Takagi-Sugeno-Kang (TSK) fuzzy classifier; deep fuzzy classifiers; fuzzy rules; gradient guided learning; large-scale datasets; stacked generalization principle

Funding

  1. National Natural Science Foundation of China [61772198, 61972181, U20A20228]
  2. Natural Science Foundation of Jiangsu Province [BK20191331, 20KJB520023]
  3. National First-class Discipline Program of Light Industry and Engineering [LITE2018]
  4. UM (University of Macao) Talent Program

Ask authors/readers for more resources

This article introduces a fast training algorithm FTA to improve the training speed and generalization capability of the deep fuzzy classifier DSA-FC on large-scale datasets. FTA downsizes fuzzy rules through gradient guided learning and trains the subclassifiers quickly at each layer.
While our recent deep fuzzy classifier DSA-FC, which stacks adversarial interpretable Takagi-Sugeno-Kang fuzzy subclassifiers, shares its promising classification, its training speed will become very slow and even intolerable for large-scale datasets, due to successive training on all training samples with their random gradient based updates along each layer of its stacked structure. In order to circumvent this bottleneck issue, a fast training algorithm FTA is developed in this study by downsizing fuzzy rules with the proposed gradient guided learning for each subclassifier at each layer of DSA-FC on large-scale datasets. The core of FTA is to assure fast training of each subclassifier at each layer of DSA-FC, which first generates first-order smooth gradient guided information by means of the proposed top-k fuzzy rules selected from all fuzzy rules in each subclassifier, and then quickly updates the current inputs in terms of such information, which will be taken as the inputs of the subclassifier at the next layer. Our theoretical analysis reveals that the proposed gradient guided learning indeed enhances the generalization capability of a deep fuzzy classifier with or without adversarial attacks on outputs. Experimental results on large datasets demonstrate that FTA indeed trains the deep fuzzy classifier DSA-FC quickly with enhanced generalization capability.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available