检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Akandeh, Atra Salem, Fathi M. Circuits Systems and Neural Networks Laboratory Computer Science and Engineering Electrical Computer Engineering Michigan State University East LansingMI48864-1226

This is part II of three-part work. Here, we present a second set of inter-related five variants of simplified Long Short-term Memory (LSTM) recurrent neural networks by further reducing adaptive parameters. Two of these models have been introduced in part I of this work. We evaluate and verify our model variants on the benchmark MNIST dataset and assert that these models are comparable to the base LSTM model while use progressively less number of parameters. Moreover, we observe that in case of using the ReLU activation, the test accuracy performance of the standard LSTM will drop after a number of epochs when learning parameter become larger. However all of the new model variants sustain their performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Simplified long short-term memory recurrent neural networks: Part i

arXiv

引用

arXiv 2017年

We present five variants of the standard Long Shortterm Memory (LSTM) recurrent neural networks by uniformly reducing blocks of adaptive parameters in the gating mechanisms. For simplicity, we refer to these models as LSTM1, LSTM2, LSTM3, LSTM4, and LSTM5, respectively. Such parameter-reduced variants enable speeding up data training computations and would be more suitable for implementations onto constrained embedded platforms. We comparatively evaluate and verify our five variant models on the classical MNIST dataset and demonstrate that these variant models are comparable to a standard implementation of the LSTM model while using less number of parameters. Moreover, we observe that in some cases the standard LSTM's accuracy performance will drop after a number of epochs when using the ReLU nonlinearity;in contrast, however, LSTM3, LSTM4 and LSTM5 will retain their performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Simplified Long Short-term memory recurrent neural networks: Part III

arXiv

引用

arXiv 2017年

This is part III of three-part work. In parts I and II, we have presented eight variants for simplified Long Short Term Memory (LSTM) recurrent neural networks (RNNs). It is noted that fast computation, specially in constrained computing resources, are an important factor in processing big timesequence data. In this part III paper, we present and evaluate two new LSTM model variants which dramatically reduce the computational load while retaining comparable performance to the base (standard) LSTM RNNs. In these new variants, we impose (Hadamard) pointwise state multiplications in the cell-memory network in addition to the gating signal networks. Copyright © 2017, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

26th Annual Computational Neuroscience Meeting (CNS*2017): Part 3 Antwerp, Belgium. 15-20 July 2017 Abstracts

引用

BMC NEUROSCIENCE 2017年第SUPPL 1期18卷 95-176页

作者： [Anonymous] Department of Neuroscience Yale University New Haven CT 06520 USA Department Physiology & Pharmacology SUNY Downstate Brooklyn NY 11203 USA NYU School of Engineering 6 MetroTech Center Brooklyn NY 11201 USA Departament de Matemàtica Aplicada Universitat Politècnica de Catalunya Barcelona 08028 Spain Institut de Neurobiologie de la Méditerrannée (INMED) INSERM UMR901 Aix-Marseille Univ Marseille France Center of Neural Science New York University New York NY USA Aix-Marseille Univ INSERM INS Inst Neurosci Syst Marseille France Laboratoire de Physique Théorique et Modélisation CNRS UMR 8089 Université de Cergy-Pontoise 95300 Cergy-Pontoise Cedex France Department of Mathematics and Computer Science ENSAT Abdelmalek Essaadi’s University Tangier Morocco Laboratory of Natural Computation Department of Information and Electrical Engineering and Applied Mathematics University of Salerno 84084 Fisciano SA Italy Department of Medicine University of Salerno 84083 Lancusi SA Italy Dipartimento di Fisica Università degli Studi Aldo Moro Bari and INFN Sezione Di Bari Italy Data Analysis Department Ghent University Ghent Belgium Coma Science Group University of Liège Liège Belgium Cruces Hospital and Ikerbasque Research Center Bilbao Spain BIOtech Department of Industrial Engineering University of Trento and IRCS-PAT FBK 38010 Trento Italy Department of Data Analysis Ghent University Ghent 9000 Belgium The Wellcome Trust Centre for Neuroimaging University College London London WC1N 3BG UK Department of Electronic Engineering NED University of Engineering and Technology Karachi Pakistan Blue Brain Project École Polytechnique Fédérale de Lausanne Lausanne Switzerland Departement of Mathematics Swansea University Swansea Wales UK Laboratory for Topology and Neuroscience at the Brain Mind Institute École polytechnique fédérale de Lausanne Lausanne Switzerland Institute of Mathematics University of Aberdeen Aberdeen Scotland UK Department of Integrativ

来源：评论

学校读者我要写书评

暂无评论

Parallel batch pattern training algorithm for deep neural network

Parallel batch pattern training algorithm for deep neural ne...

引用

International Conference on High Performance Computing & Simulation (HPCS)

作者： Volodymyr Turchenko Vladimir Golovko Research Institute for Intelligent Computer Systems Ternopil National Economic University Ternopil Ukraine Laboratory of Artificial Neural Networks Brest State Technical University Brest Belarus

ISBN: (纸本)9781479951604

The development of parallel batch pattern training algorithm for deep multilayered neural network architecture and its parallelization efficiency research on many-core system are presented in this paper. The model of a deep neural network and batch pattern training algorithm are theoretically described. The algorithmic description of the parallel batch pattern training method is presented. Our results show high parallelization efficiency of the developed algorithm on many-core parallel system with 48 CPUs with the use of message passing parallelization technology.

关键词： Training Neurons artificial neural networks Algorithm design and analysis Computer architecture Vectors Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

25th Annual Computational Neuroscience Meeting CNS-2016, Seogwipo City, South Korea, July 2-7, 2016 Abstracts

引用

BMC NEUROSCIENCE 2016年第1期17卷 1-112页

作者： [Anonymous] Computational Neurobiology Laboratory The Salk Institute for Biological Studies San Diego USA UNIC CNRS Gif sur Yvette France The European Institute for Theoretical Neuroscience (EITN) Paris France ATR Computational Neuroscience Laboratories Kyoto Japan Krembil Research Institute University Health Network Toronto Canada Department of Physiology University of Toronto Toronto Canada Department of Medicine (Neurology) University of Toronto Toronto Canada Department of Physics University of New Hampshire Durham USA Department of Neurophysiology Nencki Institute of Experimental Biology Warsaw Poland Department of Theory Wigner Research Centre for Physics of the Hungarian Academy of Sciences Budapest Hungary Department of Mathematical Sciences KAIST Daejoen Republic of Korea Department of Mathematics University of Houston Houston USA Department of Biochemistry & Cell Biology and Institute of Biosciences and Bioengineering Rice University Houston USA Department of Biology and Biochemistry University of Houston Houston USA Grupo de Neurocomputación Biológica Dpto. de Ingeniería Informática Escuela Politécnica Superior Universidad Autónoma de Madrid Madrid Spain Department of Biological Sciences University of Southern California Los Angeles USA Center for Neuroscience Korea Institute of Science and Technology Seoul South Korea Department of Neurology Albert Einstein College of Medicine Bronx USA Center for Neuroscience KIST Seoul South Korea Department of Neuroscience University of Science and Technology Daejon South Korea Systems Neuroscience Group QIMR Berghofer Medical Research Institute Herston Australia Department of Psychology Yonsei University Seoul South Korea Department of Psychiatry Kyung Hee University Hospital at Gangdong Seoul South Korea Department of Psychiatry Veterans Administration Boston Healthcare System and Harvard Medical School Brockton USA Department of Electrical and Electronic Engineering The University of Melbourne Parkvil

A1 Functional advantages of cell-type heterogeneity in neural circuits Tatyana O. Sharpee A2 Mesoscopic modeling of propagating waves in visual cortex Alain Destexhe A3 Dynamics and biomarkers of mental disorders Mitsuo Kawato F1 Precise recruitment of spiking output at theta frequencies requires dendritic h-channels in multi-compartment models of oriens-lacunosum/moleculare hippocampal interneurons Vladislav Sekulić, Frances K. Skinner F2 Kernel methods in reconstruction of current sources from extracellular potentials for single cells and the whole brains Daniel K. Wójcik, Chaitanya Chintaluri, Dorottya Cserpán, Zoltán Somogyvári F3 The synchronized periods depend on intracellular transcriptional repression mechanisms in circadian clocks. Jae Kyoung Kim, Zachary P. Kilpatrick, Matthew R. Bennett, Kresimir Josić O1 Assessing irregularity and coordination of spiking-bursting rhythms in central pattern generators Irene Elices, David Arroyo, Rafael Levi, Francisco B. Rodriguez, Pablo Varona O2 Regulation of top-down processing by cortically-projecting parvalbumin positive neurons in basal forebrain Eunjin Hwang, Bowon Kim, Hio-Been Han, Tae Kim, James T. McKenna, Ritchie E. Brown, Robert W. McCarley, Jee Hyun Choi O3 Modeling auditory stream segregation, build-up and bistability James Rankin, Pamela Osborn Popp, John Rinzel O4 Strong competition between tonotopic neural ensembles explains pitch-related dynamics of auditory cortex evoked fields Alejandro Tabas, André Rupp, Emili Balaguer-Ballester O5 A simple model of retinal response to multi-electrode stimulation Matias I. Maturana, David B. Grayden, Shaun L. Cloherty, Tatiana Kameneva, Michael R. Ibbotson, Hamish Meffin O6 Noise correlations in V4 area correlate with behavioral performance in visual discrimination task Veronika Koren, Timm Lochmann, Valentin Dragoi, Klaus Obermayer O7 Input-location dependent gain modulation in cerebellar nucleus neurons Maria Psarrou, Maria Schilstra, Neil Davey, Benjamin Torben-Ni

关键词：

来源：评论

学校读者我要写书评

暂无评论

New Blind Multiuser Detection in DS-CDMA Using H-DE and ICA Algorithms

New Blind Multiuser Detection in DS-CDMA Using H-DE and ICA ...

引用

International Conference on Intelligent systems, Modelling and Simulation (ISMS)

作者： Zaid Albataineh Fathi Salem Circuits Systems and Neural Networks Laboratory Department of Electrical and Computer Engineering Michigan State University East Lansing MI USA

Hyper Differential Evolution (H-DE)is a new optimization technique. We develop a novel blind Detection algorithm based on H-DE in conjunction with Independent Component Analysis (ICA). We then apply the algorithm to the multi-user symbol estimation problem in Direct Sequence Code Division Multiple Access (DS-CDMA) systems. Blind detection is to estimate multiple symbol sequences associated with all users in the downlink of the DS-CDMA communication system using only the received wireless data and without any knowledge of the user spreading codes. Bit error rate (BER) simulation evidence of the improved performance of this novel algorithm are shown for different number of users, signal to noise ratio (SNR) and different number of symbols per user. The performance is compared with the traditional FAST ICA Detector. The results show that the proposed algorithm performs well and outperforms the FAST ICA Detector in estimating the symbol signals from the mixed CDMA received signals.

关键词： Multiaccess communication Vectors Signal to noise ratio Bit error rate Detectors Covariance matrices Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

New Blind Multiuser Detection in DS-CDMA Based on Extension of Efficient Fast Independent Component Analysis (EF-ICA)

New Blind Multiuser Detection in DS-CDMA Based on Extension ...

引用

International Conference on Intelligent systems, Modelling and Simulation (ISMS)

作者： Zaid Albataineh Fathi Salem Circuits Systems and Neural Networks Laboratory Department of Electrical and Computer Engineering Michigan State University East Lansing MI USA

This Paper develops a novel blind Detection algorithm based on Extension of Efficient FAST Independent Component Analysis (EF-ICA). classifying the received data to many parts in order to use a fit non-quadratic function to separate a non-Gaussian source. Blind detection is to estimate multiple symbol sequences associated with all users in the downlink of the DS-CDMA communication system using only the received wireless data and without any knowledge of the user spreading codes. Bit error rate (BER) simulation evidence of the improved performance of this novel algorithm are shown for different number of users, signal to noise ratio (SNR) and different number of symbols per user. The performance is compared with several Blind Detectors based on Efficient FastICA and Fast ICA algorithms. The results show that the proposed algorithm performs well and outperforms the other Detectors in estimating the symbol signals from the mixed CDMA received signals.

关键词： Signal to noise ratio Bit error rate Multiaccess communication Algorithm design and analysis Detectors Vectors Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

New Blind Multiuser Detection DS-CDMA Algorithm Using Simplified Fourth Order Cumulant Matrices

New Blind Multiuser Detection DS-CDMA Algorithm Using Simpli...

引用

IEEE International Symposium on circuits and systems

作者： Zaid Albataineh Fathi Salem Circuits Systems And Neural Networks (CSANN) Laboratory Department of Electrical and Computer Engineering Michigan State University East Lansing Michigan 48824-1226 U.S.A.

ISBN: (纸本)9781467357609

A new blind Detection algorithm based on simplified fourth order cumulant matrices is presented and applied to the multi-user symbol estimation problem in Direct Sequence Code Division Multiple Access (DS-CDMA) systems. The blind detection is to estimate multiple symbol sequences associated with all users in the downlink of DS-CDMA communication system using only the received wireless data and without any knowledge of the user spreading codes. The proposed algorithm takes advantage of higher cumulant matrix properties to reduce computational load and enhance performance. Bit error rate (BER) simulations of this algorithm are shown for different number of users, signal to noise ratio (SNR) and different number of symbols per user in comparison with the FAST ICA algorithm and Robust ICA. The results show that the proposed algorithm outperforms the both ICA-Detectors in estimating the symbol signals from the mixed CDMA received signals.

关键词： DS-CDMA BER SNR Direct-sequence code-division multiple access signal to noise ratios Bit error rate Supernova remnants Consumers Ziziphus mauritiana wireless data Blind Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

GridSpice: A Distributed Simulation Platform for the Smart Grid

GridSpice: A Distributed Simulation Platform for the Smart G...

引用

Workshop on Modeling and Simulation of Cyber-Physical Energy systems

作者： Kyle Anderson Jimmy Du Amit Narayan Abbas El Gamal Circuits Systems and Artificial Neural Networks Laboratory Michigan State University East Lansing MI DLR - German Aerospace Center Institute of Robotics and Mechatronics Wessling Germany

ISBN: (纸本)9781479913060

GridSpice is a simulation framework for the smart grid that integrates existing electric power point tools. The framework provides computational scale and modeling capability to represent diverse scenarios in large interconnected grid systems. Currently, GridSpice integrates a transmission and economic dispatch package based on MatPOWER and the distribution system simulator Gridlab-D. GridSpice provides computational scale by parallelizing large simulation jobs across many virtual machines using Amazon Web Services. GridSpice provides three primary mechanisms for setting up simulations: a Python library, a browser-based user interface, and a Representational State Transfer (REST) API, which allows users to interface with existing data management systems or post-processing tools. GridSpice is available in open-source under the BSD license.

关键词： Power System Simulation Electric Vehicles Multiagent systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：