On the influence of synaptic weight states in a locally competitive algorithm for memristive hardware

Walt Woods, Jens Bürger, C. Teuscher
{"title":"On the influence of synaptic weight states in a locally competitive algorithm for memristive hardware","authors":"Walt Woods, Jens Bürger, C. Teuscher","doi":"10.1145/2770287.2770292","DOIUrl":null,"url":null,"abstract":"Memristors promise a means for very compact neu-romorphic nanoscale architectures that leverage in-situ learning algorithms. While traditional learning algorithms simulated in software commonly assume analog values for synaptic weights, actual physical memristors may have a finite set of achievable states during online learning. In this paper we simulate a learning algorithm with limitations on both the resolution of its weights and the means of switching between them to gain an appreciation for how these properties might affect classification performance. For our experiments we use the Locally Competitive Algorithm (LCA) by Rozell et al. in conjunction with the MNIST dataset. We investigate the effects of both linear and non-linear distributions of weight states, concluding that as long as the weights are roughly within a power law distribution close to linear the algorithm is still effective. Our results also show that the resolution required from a device depends on its transition function between states; for transitions akin to round to nearest, synaptic weights should have around 16 possible states (4-bit resolution) to obtain optimal results. We find that lowering the threshold required to change states or adding stochasticity to the system can reduce that requirement down to 4 states (2-bit resolution). The outcomes of our research are relevant for building neuromorphic hardware with state-of-the art memristive devices.","PeriodicalId":6519,"journal":{"name":"2014 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH)","volume":"38 1","pages":"19-24"},"PeriodicalIF":0.0000,"publicationDate":"2014-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2770287.2770292","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

Memristors promise a means for very compact neu-romorphic nanoscale architectures that leverage in-situ learning algorithms. While traditional learning algorithms simulated in software commonly assume analog values for synaptic weights, actual physical memristors may have a finite set of achievable states during online learning. In this paper we simulate a learning algorithm with limitations on both the resolution of its weights and the means of switching between them to gain an appreciation for how these properties might affect classification performance. For our experiments we use the Locally Competitive Algorithm (LCA) by Rozell et al. in conjunction with the MNIST dataset. We investigate the effects of both linear and non-linear distributions of weight states, concluding that as long as the weights are roughly within a power law distribution close to linear the algorithm is still effective. Our results also show that the resolution required from a device depends on its transition function between states; for transitions akin to round to nearest, synaptic weights should have around 16 possible states (4-bit resolution) to obtain optimal results. We find that lowering the threshold required to change states or adding stochasticity to the system can reduce that requirement down to 4 states (2-bit resolution). The outcomes of our research are relevant for building neuromorphic hardware with state-of-the art memristive devices.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
忆阻硬件局部竞争算法中突触权态的影响
忆阻器有望成为利用原位学习算法的非常紧凑的新形态纳米级架构的一种手段。在软件中模拟的传统学习算法通常假设突触权重的模拟值,而实际的物理忆阻器在在线学习期间可能具有有限的可实现状态集。在本文中,我们模拟了一种学习算法,该算法对其权重的分辨率和在它们之间切换的方法都有限制,以了解这些属性如何影响分类性能。在我们的实验中,我们使用了Rozell等人结合MNIST数据集的局部竞争算法(LCA)。我们研究了权重状态的线性和非线性分布的影响,得出结论,只要权重大致在接近线性的幂律分布内,算法仍然有效。我们的结果还表明,器件所需的分辨率取决于其状态之间的转换函数;对于类似于四舍五入的转换,突触权重应该有大约16种可能的状态(4位分辨率)来获得最佳结果。我们发现降低改变状态所需的阈值或向系统添加随机性可以将该要求减少到4个状态(2位分辨率)。我们的研究结果与构建具有最先进记忆装置的神经形态硬件相关。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
MECRO: A local processing computer architecture based on memristor crossbar Mosaic: A scheme of mapping non-volatile Boolean logic on memristor crossbar Wave-based multi-valued computation framework A new Tunnel-FET based RAM concept for ultra-low power applications A CMOS-memristive self-learning neural network for pattern classification applications
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1