.png){kind=icon}
.png){kind=icon}
Return
Antiforgetting Incremental Learning Algorithm for Interval Type-2 Fuzzy Neural Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TFUZZ.2023.3336325.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
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
Journal
IF:
11.9
Papers:
5.0K
Citations:
2.9W