Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 228408 | - |
dc.citation.startPage | 228392 | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 8 | - |
dc.contributor.author | Fouda, Mohammed E. | - |
dc.contributor.author | Lee, Sugil | - |
dc.contributor.author | Lee, Jongeun | - |
dc.contributor.author | Kim, Gun Hwan | - |
dc.contributor.author | Kurdahi, Fadi | - |
dc.contributor.author | Eltawil, Ahmed | - |
dc.date.accessioned | 2023-12-21T16:38:37Z | - |
dc.date.available | 2023-12-21T16:38:37Z | - |
dc.date.created | 2020-12-30 | - |
dc.date.issued | 2020-12 | - |
dc.description.abstract | Resistive Crossbar Arrays present an elegant implementation solution for Deep Neural Networks acceleration. The Matrix-Vector Multiplication, which is the corner-stone of DNNs, is carried out in O(1) compared to O(N-2) steps for digital realizations of O(log(2)(N)) steps for in-memory associative processors. However, the IR drop problem, caused by the inevitable interconnect wire resistance in RCAs remains a daunting challenge. In this article, we propose a fast and efficient training and validation framework to incorporate the wire resistance in Quantized DNNs, without the need for computationally extensive SPICE simulations during the training process. A fabricated four-bit Au/Al2O3/HfO2/TiN device is modelled and used within the framework with two-mapping schemes to realize the quantized weights. Efficient system-level IR-drop estimation methods are used to accelerate training. SPICE validation results show the effectiveness of the proposed method to capture the IR drop problem achieving the baseline accuracy with a 2% and 4% drop in the worst-case scenario for MNIST dataset on multilayer perceptron network and CIFAR 10 dataset on modified VGG and AlexNet networks, respectively. Other nonidealities, such as stuck-at fault defects, variability, and aging, are studied. Finally, the design considerations of the neuronal and the driver circuits are discussed. | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.8, pp.228392 - 228408 | - |
dc.identifier.doi | 10.1109/access.2020.3044652 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.scopusid | 2-s2.0-85098765034 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/49281 | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9293271 | - |
dc.identifier.wosid | 000604516900001 | - |
dc.language | 영어 | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | IR-QNN Framework: An IR Drop-Aware Offline Training Of Quantized Crossbar Arrays | - |
dc.type | Article | - |
dc.description.isOpenAccess | TRUE | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems; Engineering, Electrical & Electronic; Telecommunications | - |
dc.relation.journalResearchArea | Computer Science; Engineering; Telecommunications | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | RRAM | - |
dc.subject.keywordAuthor | memristor | - |
dc.subject.keywordAuthor | deep neural networks | - |
dc.subject.keywordAuthor | quantized neural networks | - |
dc.subject.keywordAuthor | IR drop | - |
dc.subject.keywordAuthor | nonidealities | - |
dc.subject.keywordAuthor | variability | - |
dc.subject.keywordAuthor | offset | - |
dc.subject.keywordPlus | NEURAL-NETWORKS | - |
dc.subject.keywordPlus | MEMRISTOR | - |
dc.subject.keywordPlus | RETENTION | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.