Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction

doi:10.1016/j.neunet.2025.108191

	Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction
	Mao, Jiayi 1; Zheng, Hanle 1; Yin, Huifeng 1; Fan, Hanxiao 1; Mei, Lingrui 2; Guo, Hao 3; Li, Yao 3; Wu, Jibin 4,5; Pei, Jing 1; Deng, Lei 1
	2026-02-01
发表期刊	NEURAL NETWORKS
ISSN	0893-6080
卷号	194 页码:15
摘要	Brain-inspired neural networks, drawing insights from biological neural systems, have emerged as a promising paradigm for temporal information processing due to their inherent neural dynamics. Spiking Neural Networks (SNNs) have gained extensive attention among existing brain-inspired neural models. However, they often struggle with capturing multi-timescale temporal features due to the static parameters across time steps and the low-precision spike activities. To this end, we propose a dynamic SNN with enhanced dendritic heterogeneity to enhance the multi-timescale feature extraction capability. We design a Leaky Integrate Modulation neuron model with Dendritic Heterogeneity (DH-LIM) that replaces traditional spike activities with a continuous modulation mechanism for preserving the nonlinear behaviors while enhancing the feature expression capability. We also introduce an Adaptive Dendritic Plasticity (ADP) mechanism that dynamically adjusts dendritic timing factors based on the frequency domain information of input signals, enabling the model to capture both rapid-and slow-changing temporal patterns. Extensive experiments on multiple datasets with rich temporal features demonstrate that our proposed method achieves excellent performance in processing complex temporal signals. These optimizations provide fresh solutions for optimizing the multi-timescale feature extraction capability of SNNs, showcasing its broad application potential.
关键词	Brain-inspired neural networks Dendritic heterogeneity LIM neurons Adaptive dendritic plasticity Multi-timescale feature extraction
DOI	10.1016/j.neunet.2025.108191
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62276151] ; Tsinghua University Initiative Scientific Research Program, Chinese Institute for Brain Research, Beijing ; Neuracle Medical Technology Co., Ltd.
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:001597588900002
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41641
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Yao; Deng, Lei
作者单位	1.Tsinghua Univ, Ctr Brain Inspired Comp Res, Dept Precis Instrument, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Ai Safety, Beijing 100190, Peoples R China 3.Taiyuan Univ Technol, Coll Comp Sci & Technol, Jinzhong 030600, Peoples R China 4.Hong Kong Polytech Univ, Dept Data Sci & Artificial Intelligence, Hong Kong, Peoples R China 5.Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Mao, Jiayi,Zheng, Hanle,Yin, Huifeng,et al. Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction[J]. NEURAL NETWORKS,2026,194:15.
APA	Mao, Jiayi.,Zheng, Hanle.,Yin, Huifeng.,Fan, Hanxiao.,Mei, Lingrui.,...&Deng, Lei.(2026).Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction.NEURAL NETWORKS,194,15.
MLA	Mao, Jiayi,et al."Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction".NEURAL NETWORKS 194(2026):15.