Academic Journal
Mixed-mode SNN crossbar array with embedded dummy switch and mid-node pre-charge scheme
Title: | Mixed-mode SNN crossbar array with embedded dummy switch and mid-node pre-charge scheme |
---|---|
Authors: | Kwang-Il Oh, Hyuk Kim, Taewook Kang, Sung-Eun Kim, Jae-Jin Lee, Byung-Do Yang |
Source: | ETRI Journal, Vol 46, Iss 5, Pp 865-877 (2024) |
Publisher Information: | Electronics and Telecommunications Research Institute (ETRI), 2024. |
Publication Year: | 2024 |
Collection: | LCC:Telecommunication LCC:Electronics |
Subject Terms: | charge sharing, crossbar array, digital-to-analog converter, mixed mode, neuromorphic system, spiking neural network, synapse, Telecommunication, TK5101-6720, Electronics, TK7800-8360 |
More Details: | This paper presents a membrane computation error-minimized mixed-mode spiking neural network (SNN) crossbar array. Our approach involves imple-menting an embedded dummy switch scheme and a mid-node pre-charge scheme to construct a high-precision current-mode synapse. We effectively suppressed charge sharing between membrane capacitors and the parasitic capacitance of synapses that results in membrane computation error. A 400 X 20 SNN crossbar prototype chip is fabricated via a 28-nm FDSOI CMOS process, and 20 MNIST patterns with their sizes reduced to 20 X 20 pixels are successfully recognized under 411 μW of power consumed. Moreover, the peak-to-peak deviation of the normalized output spike count measured from the 21 fabricated SNN prototype chips is within 16.5% from the ideal value, including sample-wise random variations. |
Document Type: | article |
File Description: | electronic resource |
Language: | English |
ISSN: | 2024-0120 1225-6463 2233-7326 |
Relation: | https://doaj.org/toc/1225-6463; https://doaj.org/toc/2233-7326 |
DOI: | 10.4218/etrij.2024-0120 |
Access URL: | https://doaj.org/article/f7ddd1eb2f51412fb390eccb58edd96f |
Accession Number: | edsdoj.f7ddd1eb2f51412fb390eccb58edd96f |
Database: | Directory of Open Access Journals |
Full text is not displayed to guests. | Login for full access. |
ISSN: | 20240120 12256463 22337326 |
---|---|
DOI: | 10.4218/etrij.2024-0120 |
Published in: | ETRI Journal |
Language: | English |