Incorporating structural plasticity into self-organization recurrent networks for sequence learning

文献类型： 外文期刊

第一作者： Yuan, Ye

作者： Yuan, Ye;Zhu, Yongtong;Wang, Jiaqi;Li, Ruoshi;Xu, Xin;Li, Qingdu;Liu, Na;Fang, Tao;Huo, Hong;Wan, Lihong;Yang, Shiyan

作者机构：

关键词： spiking neural network; self-organization; reward-modulated spike timing-dependent plasticity; homeostatic plasticity; structural plasticity

期刊名称：FRONTIERS IN NEUROSCIENCE （ 影响因子：4.3； 五年影响因子：5.2 ）

ISSN：

年卷期： 2023 年 17 卷

页码：

收录情况： SCI

摘要： 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.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序