Gradient-Optimized Fuzzy Classifier: A Benchmark Study Against State-of-the-Art Models

TL;DR

The study benchmarks a Gradient-Optimized Fuzzy Inference System (GF) against several state-of-the-art models on five diverse UCI datasets to assess accuracy and training efficiency. By training a fuzzy inference system with gradient descent (via ADAM on GPU) and cross-entropy loss, GF achieves competitive or superior performance in many cases while delivering notably faster training times. Across Statlog, Breast Cancer Wisconsin, Car Evaluation, Heart Disease, and Wine datasets, GF demonstrates robustness to noisy data and maintains stable performance, highlighting its potential as an interpretable and efficient alternative to deeper networks in supervised classification. These findings underscore the practical viability of gradient-optimized fuzzy classifiers for real-world tasks where interpretability and speed are prioritized, with room for further enhancements such as early stopping and adaptive learning rates.

Abstract

This paper presents a performance benchmarking study of a Gradient-Optimized Fuzzy Inference System (GF) classifier against several state-of-the-art machine learning models, including Random Forest, XGBoost, Logistic Regression, Support Vector Machines, and Neural Networks. The evaluation was conducted across five datasets from the UCI Machine Learning Repository, each chosen for their diversity in input types, class distributions, and classification complexity. Unlike traditional Fuzzy Inference Systems that rely on derivative-free optimization methods, the GF leverages gradient descent to significantly improving training efficiency and predictive performance. Results demonstrate that the GF model achieved competitive, and in several cases superior, classification accuracy while maintaining high precision and exceptionally low training times. In particular, the GF exhibited strong consistency across folds and datasets, underscoring its robustness in handling noisy data and variable feature sets. These findings support the potential of gradient optimized fuzzy systems as interpretable, efficient, and adaptable alternatives to more complex deep learning models in supervised learning tasks.