Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning
Self-organizing Map (SOM) neural network is a prominent algorithm in unsupervised machine learning, which is widely used for data clustering, high-dimensional visualization, and feature extraction. However, the hardware implementation of SOM is limited by the von Neumann bottleneck. Herein, a SOM ne...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of the Electron Devices Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10333078/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583223099523072 |
|---|---|
| author | Anyi Zhu Lei Jin Wen Zhou Tianchun Ye Zongliang Huo |
| author_facet | Anyi Zhu Lei Jin Wen Zhou Tianchun Ye Zongliang Huo |
| author_sort | Anyi Zhu |
| collection | DOAJ |
| description | Self-organizing Map (SOM) neural network is a prominent algorithm in unsupervised machine learning, which is widely used for data clustering, high-dimensional visualization, and feature extraction. However, the hardware implementation of SOM is limited by the von Neumann bottleneck. Herein, a SOM neural network is implemented by the combination of 3D NAND flash memory arrays and in-memory Euclidean distance (ED) calculation. The weights in the SOM network are mapped to the conductance of the 3D NAND differential pair. It is experimentally demonstrated that the differential pair in 3D NAND flash array possesses superior characteristics for neuromorphic computing during increasing and decreasing synaptic weight. Using the 3D NAND-based SOM, a competitive learning neural network is established and used for the unsupervised classification of a set of Gaussian distribution data points. The experimental results illustrate the excellent performance and efficiency of the proposed architecture, highlighting the potential of 3D NAND-based in-memory computing for artificial intelligence applications. |
| format | Article |
| id | doaj-art-50c97da1380d47cd8a8d943392c14e72 |
| institution | Kabale University |
| issn | 2168-6734 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of the Electron Devices Society |
| spelling | doaj-art-50c97da1380d47cd8a8d943392c14e722025-01-29T00:00:09ZengIEEEIEEE Journal of the Electron Devices Society2168-67342024-01-0112232710.1109/JEDS.2023.333739910333078Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive LearningAnyi Zhu0https://orcid.org/0009-0005-9794-4001Lei Jin1Wen Zhou2https://orcid.org/0000-0002-9037-1803Tianchun Ye3https://orcid.org/0000-0002-2384-9037Zongliang Huo4https://orcid.org/0000-0002-9845-5649Institute 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, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaInstitute of Microelectronics of the Chinese Academy of Sciences, Beijing, ChinaSelf-organizing Map (SOM) neural network is a prominent algorithm in unsupervised machine learning, which is widely used for data clustering, high-dimensional visualization, and feature extraction. However, the hardware implementation of SOM is limited by the von Neumann bottleneck. Herein, a SOM neural network is implemented by the combination of 3D NAND flash memory arrays and in-memory Euclidean distance (ED) calculation. The weights in the SOM network are mapped to the conductance of the 3D NAND differential pair. It is experimentally demonstrated that the differential pair in 3D NAND flash array possesses superior characteristics for neuromorphic computing during increasing and decreasing synaptic weight. Using the 3D NAND-based SOM, a competitive learning neural network is established and used for the unsupervised classification of a set of Gaussian distribution data points. The experimental results illustrate the excellent performance and efficiency of the proposed architecture, highlighting the potential of 3D NAND-based in-memory computing for artificial intelligence applications.https://ieeexplore.ieee.org/document/10333078/Self-organizing map (SOM)3D NAND Flashcompetitive learningin-memory computing |
| spellingShingle | Anyi Zhu Lei Jin Wen Zhou Tianchun Ye Zongliang Huo Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning IEEE Journal of the Electron Devices Society Self-organizing map (SOM) 3D NAND Flash competitive learning in-memory computing |
| title | Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning |
| title_full | Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning |
| title_fullStr | Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning |
| title_full_unstemmed | Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning |
| title_short | Self-Organizing Mapping Neural Network Implementation Based on 3-D NAND Flash for Competitive Learning |
| title_sort | self organizing mapping neural network implementation based on 3 d nand flash for competitive learning |
| topic | Self-organizing map (SOM) 3D NAND Flash competitive learning in-memory computing |
| url | https://ieeexplore.ieee.org/document/10333078/ |
| work_keys_str_mv | AT anyizhu selforganizingmappingneuralnetworkimplementationbasedon3dnandflashforcompetitivelearning AT leijin selforganizingmappingneuralnetworkimplementationbasedon3dnandflashforcompetitivelearning AT wenzhou selforganizingmappingneuralnetworkimplementationbasedon3dnandflashforcompetitivelearning AT tianchunye selforganizingmappingneuralnetworkimplementationbasedon3dnandflashforcompetitivelearning AT zonglianghuo selforganizingmappingneuralnetworkimplementationbasedon3dnandflashforcompetitivelearning |