T2FELA: type-2 fuzzy extreme learning algorithm for fast training of interval type-2 TSK fuzzy logic system.

Area of Science:

• Computational Intelligence
• Fuzzy Logic Systems
• Machine Learning

Background:

• Modeling large-scale real-world datasets with type-2 fuzzy logic systems presents challenges in developing efficient learning algorithms.
• Existing algorithms struggle with the computational demands of increasing data sizes.

Purpose of the Study:

• To introduce an efficient and fast training algorithm for interval type-2 Takagi-Sugeno-Kang fuzzy logic systems.
• To address the limitations of current learning strategies in handling large datasets.

Main Methods:

• The proposed algorithm, Type-2 Fuzzy Extreme Learning Algorithm (T2FELA), utilizes an extreme learning strategy.
• Antecedent parameters are randomly generated, while consequent parameters are determined through a rapid learning mechanism.
• Parameters are optimized to minimize the norm, enhancing generalization.

Main Results:

• T2FELA demonstrates superior training speed compared to existing state-of-the-art algorithms.
• The algorithm achieves competitive generalization performance.
• Experimental results validate the efficiency and effectiveness of T2FELA.

Conclusions:

• The T2FELA algorithm offers a significant advancement in training speed for interval type-2 fuzzy logic systems.
• The method provides a robust solution for modeling large and complex datasets.
• T2FELA enhances the practical applicability of type-2 fuzzy logic systems in real-world scenarios.