Transfer Learning of Fuzzy Spatio-Temporal Rules in a Brain-Inspired Spiking Neural Network Architecture: A Case Study on Spatio-Temporal Brain Data

• Published in: IEEE transactions on fuzzy systems Vol. 31; no. 12; pp. 4542 - 4552
• Main Authors: Kasabov, Nikola K., Tan, Yongyao, Doborjeh, Maryam, Tu, Enmei, Yang, Jie, Goh, Wilson, Lee, Jimmy
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bio-inspired engineering; Brain; EEG data; Electroencephalography; explainable AI; fuzzy spatio-temporal rules; Knowledge management; neucube; Neural networks; Neurons; spatio-temporal learning; Spatiotemporal data; spiking neural networks; Three-dimensional displays; Transfer learning
• ISSN: 1063-6706; 1941-0034
• DOI: 10.1109/TFUZZ.2023.3292802

The article demonstrates for the first time that a brain-inspired spiking neural network (SNN) architecture can be used not only to learn spatio-temporal data, but also to extract fuzzy spatio-temporal rules from such data and to update these rules incrementally in a transfer learning mode. We propose a method, where a SNN model learns incrementally new time-space data related to new classes/tasks/categories, always utilizing some previously learned knowledge, and presents the evolved knowledge as fuzzy spatio-temporal rules. Similarly, to how the brain manifests transfer learning, these SNN models do not need to be restricted in number of layers and neurons in each layer as they adopt self-organizing learning principles. The continuously evolved fuzzy rules from spatio-temporal data are interpretable for a better understanding of the processes that generate the data. The proposed method is based on a brain-inspired SNN architecture NeuCube, which is structured according to a brain three-dimensional structural template. It is illustrated on tasks of incremental and transfer learning and knowledge transfer using spatio-temporal data measuring brain activity, when subjects are performing tasks in space and time. The method is a general one and opens the field to create new types of adaptable and explainable spatio-temporal learning systems across domain areas.