An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections
文献类型:期刊论文
作者 | Dong, Yiting1,3; Zhao, Dongcheng3; Li, Yang3,4; Zeng, Yi1,2,3,4,5 |
刊名 | NEURAL NETWORKS |
出版日期 | 2023-08-01 |
卷号 | 165页码:799-808 |
ISSN号 | 0893-6080 |
关键词 | Spiking neural network Unsupervised Plasticity learning rule Brain inspired connection |
DOI | 10.1016/j.neunet.2023.06.019 |
通讯作者 | Zeng, Yi(yi.zeng@ia.ac.cn) |
英文摘要 | The backpropagation algorithm has promoted the rapid development of deep learning, but it relies on a large amount of labeled data and still has a large gap with how humans learn. The human brain can quickly learn various conceptual knowledge in a self-organized and unsupervised manner, accomplished through coordinating various learning rules and structures in the human brain. Spiketiming-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. In this paper, taking inspiration from short-term synaptic plasticity, we design an adaptive synaptic filter and introduce the adaptive spiking threshold as the neuron plasticity to enrich the representation ability of SNNs. We also introduce an adaptive lateral inhibitory connection to adjust the spikes balance dynamically to help the network learn richer features. To speed up and stabilize the training of unsupervised spiking neural networks, we design a samples temporal batch STDP (STB-STDP), which updates weights based on multiple samples and moments. By integrating the above three adaptive mechanisms and STB-STDP, our model greatly accelerates the training of unsupervised spiking neural networks and improves the performance of unsupervised SNNs on complex tasks. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets. Further, we tested on the more complex CIFAR10 dataset, and the results fully illustrate the superiority of our algorithm. Our model is also the first work to apply unsupervised STDP-based SNNs to CIFAR10. At the same time, in the small-sample learning scenario, it will far exceed the supervised ANN using the same structure. & COPY; 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
WOS关键词 | LATERAL-INHIBITION ; PLASTICITY ; NEURONS |
资助项目 | National Key Research and De- velopment Program[XDB32070100] ; Strategic Priority Research Program of the Chinese Academy of Sciences ; [2020AAA0107800] |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:001057996700001 |
资助机构 | National Key Research and De- velopment Program ; Strategic Priority Research Program of the Chinese Academy of Sciences |
源URL | [http://ir.ia.ac.cn/handle/173211/54107] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zeng, Yi |
作者单位 | 1.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China 2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China 3.Chinese Acad Sci, Inst Automat, Brain Inspired Cognit Intelligence Lab, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artifcial Intelligence Sy, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Dong, Yiting,Zhao, Dongcheng,Li, Yang,et al. An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections[J]. NEURAL NETWORKS,2023,165:799-808. |
APA | Dong, Yiting,Zhao, Dongcheng,Li, Yang,&Zeng, Yi.(2023).An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections.NEURAL NETWORKS,165,799-808. |
MLA | Dong, Yiting,et al."An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections".NEURAL NETWORKS 165(2023):799-808. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。