Circuit Implementation of Data-Driven TSK-Type Interval Type-2 Neural Fuzzy System With Online Parameter Tuning Ability

This paper proposes a new circuit for implementing a reduced-interval type-2 neural fuzzy system using weighted bound-set boundaries (RIT2NFS-WB) with online tuning ability. The antecedent and consequent parts of the RIT2NFS-WB use interval type-2 fuzzy sets and Takagi-Sugeno-Kang (TSK) rules with interval combination parameters, respectively. In the software implementation, the structure and parameters of the RIT2NFS-WB are learned through firing-strength-based rule generation and gradient descent algorithms, respectively. The software-designed RIT2NFS-WB is then transferred to a circuit implementation with online parameter-tuning ability; the hardware version is called the RIT2NFS-WB(HL). The RIT2NFS-WB(HL) is characterized by its online tuning ability with updatable consequent and weighting parameters. To the best of our knowledge, the RIT2NFS-WB(HL) is the first TSK-type interval type-2 neural fuzzy circuit with online parameter tuning ability in the literature. To take advantage of the inherent parallel processing property of the rules, a parallel processing technique is utilized in the RIT2NFS-WB(HL) to achieve computational speedup. The RIT2NFS-WB(HL) is applied to examples of online system modeling and sequence prediction to demonstrate the system's functionality.