Antiforgetting Incremental Learning Algorithm for Interval Type-2 Fuzzy Neural Network

Chenxuan Sun

doi:10.1109/TFUZZ.2023.3336325

2024-04-01

PRE

DOI：10.1109/TFUZZ.2023.3336325

原文链接

原文求助

摘要

En 中文

Sample property drift is an essential issue for interval type-2 fuzzy neural networks (IT2FNNs). When the samples with fresh properties appear, IT2FNN invariably suffers from catastrophic forgetting due to the modification of its numerous parameters. To solve this problem, an antiforgetting incremental learning algorithm is proposed to update IT2FNN. First, a double-displacement indicator (DDI) is designed to detect when catastrophic forgetting occurs caused by property drift. It integrates the indicators from the feature and target spaces to avoid missing detection of property breakpoints. Second, a multilevel learning objective is developed to perceive catastrophic forgetting. The convergence, diversity, and stability criteria of fuzzy rules are embedded into the objective to improve the compatibility of IT2FNN for different properties. Third, an adaptive hierarchical update strategy (AHUS) is proposed to update the parameters of IT2FNN. With AHUS, the parameters are shared among samples with different properties, which can alleviate catastrophic forgetting. Finally, some experiments have verified that the performance of the presented method is superior to other methods in dynamic system identification.

Keyword:

Task analysis

Neurons

Fuzzy neural networks

Computational modeling

Training

Dynamical systems

Adaptation models

Anti-forgetting incremental learning algorithm

catastrophic forgetting

interval type-2 fuzzy neural network

property drift