TSK-Streams: Learning TSK Fuzzy Systems on Data Streams

TL;DR

TSK-Streams introduces a novel approach combining rule-based incremental learning with fuzzy systems to adaptively model evolving data streams, demonstrating high performance in experiments.

Contribution

The paper presents TSK-Streams, a new method that merges AMRules principles with fuzzy rule representations for improved data stream learning.

Findings

Highly competitive performance in experiments

Effective handling of non-stationary data streams

Combines strengths of existing learning paradigms

Abstract

The problem of adaptive learning from evolving and possibly non-stationary data streams has attracted a lot of interest in machine learning in the recent past, and also stimulated research in related fields, such as computational intelligence and fuzzy systems. In particular, several rule-based methods for the incremental induction of regression models have been proposed. In this paper, we develop a method that combines the strengths of two existing approaches rooted in different learning paradigms. More concretely, our method adopts basic principles of the state-of-the-art learning algorithm AMRules and enriches them by the representational advantages of fuzzy rules. In a comprehensive experimental study, TSK-Streams is shown to be highly competitive in terms of performance.