Blended Glial Cell’s Spiking Neural Network
Spiking Neural Networks (SNNs), the third generation of artificial neural networks, have been widely employed. However, the realization of advanced artificial intelligence is challenging due to the dearth of efficient spatiotemporal information integration models. Inspired by brain neuroscientists,...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10103904/ |
| _version_ | 1797805950707433472 |
|---|---|
| author | Liying Tao Pan Li Meihua Meng Zonglin Yang Xiaozhuang Liu Jinhua Hu Ji Dong Shushan Qiao Tianchun Ye Delong Shang |
| author_facet | Liying Tao Pan Li Meihua Meng Zonglin Yang Xiaozhuang Liu Jinhua Hu Ji Dong Shushan Qiao Tianchun Ye Delong Shang |
| author_sort | Liying Tao |
| collection | DOAJ |
| description | Spiking Neural Networks (SNNs), the third generation of artificial neural networks, have been widely employed. However, the realization of advanced artificial intelligence is challenging due to the dearth of efficient spatiotemporal information integration models. Inspired by brain neuroscientists, this paper proposes a novel spiking neural network - Blended Glial Cell’s Spiking Neural Network (BGSNN). BGSNN introduces glial cells as spatiotemporal information processing units based on neurons and synapses, and also provides four new network dynamics connection models which extend the information processing dimension, enhance the network global information integration in the spatiotemporal domain, as well as the plasticity of neurons and synapses. In this paper, a BGSNN application - Sudoku solver is designed and implemented on the “WenTian” neuromorphic prototype. On the Easybrain dataset, the BGSNN solver achieves 100% accuracy, outperforming the same structure SNN solver by 97% at the Evil difficulty level, and has faster converges speed compared with the SOTA Sudoku solver LSGA. On the kaggle dataset, the BGSNN solver achieves over 99.99% accuracy, outperforming the publicly available optimal DNN solver under this dataset by 3.82%. In addition, BGSNN exhibits good parallelism and sparsity, decreasing computation by at least 92.9% compared to serial solvers and reducing sparsity by 88% compared to the equal fully dense DNN. BGSNN improves the expression, feedback, and regulation capabilities of neural networks while maintaining the advantages of SNN parallel sparsity, making it simpler to implement advanced artificial intelligence. |
| first_indexed | 2024-03-13T06:00:14Z |
| format | Article |
| id | doaj.art-89d69bfd70b94b73b8084cf6693d5564 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T06:00:14Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-89d69bfd70b94b73b8084cf6693d55642023-06-12T23:01:27ZengIEEEIEEE Access2169-35362023-01-0111435664358210.1109/ACCESS.2023.326785610103904Blended Glial Cell’s Spiking Neural NetworkLiying Tao0https://orcid.org/0000-0003-0189-4694Pan Li1Meihua Meng2Zonglin Yang3Xiaozhuang Liu4Jinhua Hu5Ji Dong6Shushan Qiao7https://orcid.org/0000-0002-9102-2111Tianchun Ye8https://orcid.org/0000-0002-2384-9037Delong Shang9Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaNanjing Institute of Intelligent Technology, Nanjing, ChinaNanjing Institute of Intelligent Technology, Nanjing, ChinaNanjing Institute of Intelligent Technology, Nanjing, ChinaNanjing Institute of Intelligent Technology, Nanjing, ChinaNanjing Institute of Intelligent Technology, Nanjing, ChinaSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaSpiking Neural Networks (SNNs), the third generation of artificial neural networks, have been widely employed. However, the realization of advanced artificial intelligence is challenging due to the dearth of efficient spatiotemporal information integration models. Inspired by brain neuroscientists, this paper proposes a novel spiking neural network - Blended Glial Cell’s Spiking Neural Network (BGSNN). BGSNN introduces glial cells as spatiotemporal information processing units based on neurons and synapses, and also provides four new network dynamics connection models which extend the information processing dimension, enhance the network global information integration in the spatiotemporal domain, as well as the plasticity of neurons and synapses. In this paper, a BGSNN application - Sudoku solver is designed and implemented on the “WenTian” neuromorphic prototype. On the Easybrain dataset, the BGSNN solver achieves 100% accuracy, outperforming the same structure SNN solver by 97% at the Evil difficulty level, and has faster converges speed compared with the SOTA Sudoku solver LSGA. On the kaggle dataset, the BGSNN solver achieves over 99.99% accuracy, outperforming the publicly available optimal DNN solver under this dataset by 3.82%. In addition, BGSNN exhibits good parallelism and sparsity, decreasing computation by at least 92.9% compared to serial solvers and reducing sparsity by 88% compared to the equal fully dense DNN. BGSNN improves the expression, feedback, and regulation capabilities of neural networks while maintaining the advantages of SNN parallel sparsity, making it simpler to implement advanced artificial intelligence.https://ieeexplore.ieee.org/document/10103904/Glial cellspiking neural networksspatiotemporal information integrationsudoku solver |
| spellingShingle | Liying Tao Pan Li Meihua Meng Zonglin Yang Xiaozhuang Liu Jinhua Hu Ji Dong Shushan Qiao Tianchun Ye Delong Shang Blended Glial Cell’s Spiking Neural Network IEEE Access Glial cell spiking neural networks spatiotemporal information integration sudoku solver |
| title | Blended Glial Cell’s Spiking Neural Network |
| title_full | Blended Glial Cell’s Spiking Neural Network |
| title_fullStr | Blended Glial Cell’s Spiking Neural Network |
| title_full_unstemmed | Blended Glial Cell’s Spiking Neural Network |
| title_short | Blended Glial Cell’s Spiking Neural Network |
| title_sort | blended glial cell x2019 s spiking neural network |
| topic | Glial cell spiking neural networks spatiotemporal information integration sudoku solver |
| url | https://ieeexplore.ieee.org/document/10103904/ |
| work_keys_str_mv | AT liyingtao blendedglialcellx2019sspikingneuralnetwork AT panli blendedglialcellx2019sspikingneuralnetwork AT meihuameng blendedglialcellx2019sspikingneuralnetwork AT zonglinyang blendedglialcellx2019sspikingneuralnetwork AT xiaozhuangliu blendedglialcellx2019sspikingneuralnetwork AT jinhuahu blendedglialcellx2019sspikingneuralnetwork AT jidong blendedglialcellx2019sspikingneuralnetwork AT shushanqiao blendedglialcellx2019sspikingneuralnetwork AT tianchunye blendedglialcellx2019sspikingneuralnetwork AT delongshang blendedglialcellx2019sspikingneuralnetwork |