A Layered Spiking Neural System for Classification Problems

Zhang, Gexiang; Zhang, Xihai; Rong, Haina; Paul, Prithwineel; Zhu, Ming; Neri, Ferrante; Ong, Yew-Soon

Abstract

Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving high classification performance are gaining momentum. Spiking neural P systems (SN P systems) are a class of membrane computing models and third-generation neural networks that are based on the behavior of biological neural cells and have been used in various engineering applications. Furthermore, SN P systems are characterized by a highly flexible structure that enables the design of a machine learning algorithm by mimicking the structure and behavior of biological cells without the over-simplification present in neural networks. Based on this aspect, this paper proposes a novel type of SN P system, namely, layered SN P system (LSN P system), to solve classification problems by supervised learning. The proposed LSN P system consists of a multi-layer network containing multiple weighted fuzzy SN P systems with adaptive weight adjustment rules. The proposed system employs specific ascending dimension techniques and a selection method of output neurons for classification problems. The experimental results obtained using benchmark datasets from the UCI machine learning repository and MNIST dataset demonstrated the feasibility and effectiveness of the proposed LSN P system. More importantly, the proposed LSN P system presents the first SN P system that demonstrates sufficient performance for use in addressing real-world classification problems.

Citation

Zhang, G., Zhang, X., Rong, H., Paul, P., Zhu, M., Neri, F., & Ong, Y.-S. (2022). A Layered Spiking Neural System for Classification Problems. International Journal of Neural Systems, 32(8), Article 2250023. https://doi.org/10.1142/S012906572250023X

• Journal Article Type: Article
• Acceptance Date: Feb 26, 2022
• Online Publication Date: Apr 12, 2022
• Publication Date: 2022-08
• Deposit Date: Mar 8, 2022
• Publicly Available Date: Apr 13, 2023
• Journal: International Journal of Neural Systems
• Print ISSN: 0129-0657
• Electronic ISSN: 1793-6462
• Publisher: World Scientific
• Peer Reviewed: Peer Reviewed
• Volume: 32
• Issue: 8
• Article Number: 2250023
• DOI: https://doi.org/10.1142/S012906572250023X
• Keywords: Spiking neural networks; Spiking neural P systems; layered weighted fuzzy spiking neural P systems; supervised learning
• Public URL: https://nottingham-repository.worktribe.com/output/7564509
• Publisher URL: https://www.worldscientific.com/doi/10.1142/S012906572250023X
• Additional Information: Electronic version of an article published as A Layered Spiking Neural System for Classification Problems; Gexiang Zhang (1School of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, P. R. China), Xihai Zhang (2School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, P. R. China), Haina Rong (3School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China), Prithwineel Paul (1School of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, P. R. China), Ming Zhu (1School of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, P. R. China), Ferrante Neri (4NICE Group, Department of Computer Science, University of Surrey, UK), and Yew-Soon Ong (5School of Computer Science and Engineering, Nanyang Technological University, Singapore); International Journal of Neural Systems https://doi.org/10.1142/S012906572250023X © [copyright World Scientific Publishing Company] https://www.worldscientific.com/worldscinet/ijns