An analysis of Dynamic Cortex Memory networks

S. Otte, A. Zell, M. Liwicki
{"title":"An analysis of Dynamic Cortex Memory networks","authors":"S. Otte, A. Zell, M. Liwicki","doi":"10.1109/IJCNN.2015.7280753","DOIUrl":null,"url":null,"abstract":"The recently introduced Dynamic Cortex Memory (DCM) is an extension of the Long Short Term Memory (LSTM) providing a systematic inter-gate connection infrastructure. In this paper the behavior of DCM networks is studied in more detail and their potential in the field of gradient-based sequence learning is investigated. Hereby, DCM networks are analyzed regarding particular key features of neural signal processing systems, namely, their robustness to noise and their ability of time warping. Throughout all experiments we show that DCMs converge faster and yield better results than LSTMs. Hereby, DCM networks require overall less weights than pure LSTM networks to achieve the same or even better results. Besides, a promising neurally implemented just-in-time online signal filter approach is presented, which is latency-free and still provides an accurate filtering performance much better than conventional low-pass filters. We also show that the neural networks can do explicit time warping even better than the Dynamic Time Warping (DTW) algorithm, which is a specialized method developed for this task.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"2 1","pages":"1-8"},"PeriodicalIF":0.0000,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Joint Conference on Neural Networks (IJCNN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IJCNN.2015.7280753","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

Abstract

The recently introduced Dynamic Cortex Memory (DCM) is an extension of the Long Short Term Memory (LSTM) providing a systematic inter-gate connection infrastructure. In this paper the behavior of DCM networks is studied in more detail and their potential in the field of gradient-based sequence learning is investigated. Hereby, DCM networks are analyzed regarding particular key features of neural signal processing systems, namely, their robustness to noise and their ability of time warping. Throughout all experiments we show that DCMs converge faster and yield better results than LSTMs. Hereby, DCM networks require overall less weights than pure LSTM networks to achieve the same or even better results. Besides, a promising neurally implemented just-in-time online signal filter approach is presented, which is latency-free and still provides an accurate filtering performance much better than conventional low-pass filters. We also show that the neural networks can do explicit time warping even better than the Dynamic Time Warping (DTW) algorithm, which is a specialized method developed for this task.
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
动态皮层记忆网络的分析
最近推出的动态皮层记忆(DCM)是长短期记忆(LSTM)的扩展,提供了系统的门间连接基础设施。本文更详细地研究了DCM网络的行为,并探讨了其在基于梯度的序列学习领域的潜力。因此,针对神经信号处理系统的特定关键特征,即对噪声的鲁棒性和时间翘曲能力,对DCM网络进行了分析。在所有的实验中,我们证明了dcm比lstm收敛得更快,并且产生了更好的结果。因此,与纯LSTM网络相比,DCM网络总体上需要更少的权重来获得相同甚至更好的结果。此外,提出了一种有前途的神经实现的实时在线信号滤波方法,该方法在无延迟的情况下仍然提供比传统低通滤波器更好的精确滤波性能。我们还表明,神经网络可以做显式时间翘曲,甚至比动态时间翘曲(DTW)算法更好,动态时间翘曲(DTW)算法是为此任务开发的专门方法。
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
Efficient conformal regressors using bagged neural nets Repeated play of the SVM game as a means of adaptive classification Unit commitment considering multiple charging and discharging scenarios of plug-in electric vehicles High-dimensional function approximation using local linear embedding A label compression coding approach through maximizing dependence between features and labels for multi-label classification
×
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