Home »
Academic Articles »
C »
Incorporating structural plasticity into self-organization recurrent networks for sequence learning
Incorporating structural plasticity into self-organization recurrent networks for sequence learning
Ye Yuan
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Yongtong Zhu
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Jiaqi Wang
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Ruoshi Li
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Xin Xu
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Tao Fang
(Automation of Department, Shanghai Jiao Tong University, Shanghai, China)
Hong Huo
(Automation of Department, Shanghai Jiao Tong University, Shanghai, China)
Lihong Wan
(Origin Dynamics Intelligent Robot Co., Ltd., Zhengzhou, China)
Qingdu Li
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Na Liu
(School of Health Science and Engineering, Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, China)
Shiyan Yang
(Eco-Environmental Protection Institution, Shanghai Academy of Agricultural Sciences, Shanghai, China)
Journal: Frontiers in Neuroscience
•
• Frontiers Media S.A.
• ISSN: 1662-453X
Abstract
IntroductionSpiking neural networks (SNNs), inspired by biological neural networks, have received a surge of interest due to its temporal encoding. Biological neural networks are driven by multiple plasticities, including spike timing-dependent plasticity (STDP), structural plasticity, and homeostatic plasticity, making network connection patterns and weights to change continuously during the lifecycle. However, it is unclear how these plasticities interact to shape neural networks and affect neural signal processing.MethodHere, we propose a reward-modulated self-organization recurrent network with structural plasticity (RSRN-SP) to investigate this issue. Specifically, RSRN-SP uses spikes to encode information, and incorporate multiple plasticities including reward-modulated spike timing-dependent plasticity (R-STDP), homeostatic plasticity, and structural plasticity. On the one hand, combined with homeostatic plasticity, R-STDP is presented to guide the updating of synaptic weights. On the other hand, structural plasticity is utilized to simulate the growth and pruning of synaptic connections.Results and discussionExtensive experiments for sequential learning tasks are conducted to demonstrate the representational ability of the RSRN-SP, including counting task, motion prediction, and motion generation. Furthermore, the simulations also indicate that the characteristics arose from the RSRN-SP are consistent with biological observations.
Ye Yuan, Yongtong Zhu, Jiaqi Wang, et al. (2023). "Incorporating structural plasticity into self-organization recurrent networks for sequence learning". Frontiers in Neuroscience. https://doi.org/10.3389/fnins.2023.1224752