检索结果-内蒙古大学图书馆

Deep net triage: Analyzing the importance of network layers via structural compression

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Nowak, Theodore S. Corso, Jason J. Robotics Institute University of Michigan Ann ArborMI48109 United States Robotics Institute Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

Despite their prevalence, deep networks are poorly understood. This is due, at least in part, to their highly parameterized nature. As such, while certain structures have been found to work better than others, the significance of a model's unique structure, or the importance of a given layer, and how these translate to overall accuracy, remains unclear. In this paper, we analyze these properties of deep neural networks via a process we term deep net triage. Like medical triage-the assessment of the importance of various wounds-we assess the importance of layers in a neural network, or as we call it, their criticality. We do this by applying structural compression, whereby we reduce a block of layers to a single layer. After compressing a set of layers, we apply a combination of initialization and training schemes, and look at network accuracy, convergence, and the layer's learned filters to assess the criticality of the layer. We apply this analysis across four data sets of varying complexity. We find that the accuracy of the model does not depend on which layer was compressed;that accuracy can be recovered or exceeded after compression by fine-tuning across the entire model;and, lastly, that Knowledge Distillation can be used to hasten convergence of a compressed network, but constrains the accuracy attainable to that of the base model. Copyright © 2018, The Authors. All rights reserved.

关键词： Distillation

A variational feature encoding method of 3d object for probabilistic semantic SLAM

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, H.W. Lee, B.H. Automation and Systems Research Institute Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

This paper presents a feature encoding method of complex 3D objects for high-level semantic features. Recent approaches to object recognition methods become important for semantic simultaneous localization and mapping (SLAM). However, there is a lack of consideration of the probabilistic observation model for 3D objects, as the shape of a 3D object basically follows a complex probability distribution. Furthermore, since the mobile robot equipped with a range sensor observes only a single view, much information of the object shape is discarded. These limitations are the major obstacles to semantic SLAM and view-independent loop closure using 3D object shapes as features. In order to enable the numerical analysis for the Bayesian inference, we approximate the true observation model of 3D objects to tractable distributions. Since the observation likelihood can be obtained from the generative model, we formulate the true generative model for 3D object with the Bayesian networks. To capture these complex distributions, we apply a variational auto-encoder. To analyze the approximated distributions and encoded features, we perform classification with maximum likelihood estimation and shape retrieval. Copyright © 2018, The Authors. All rights reserved.

关键词： Signal encoding

Self-Awareness for Autonomous systems

学校读者我要写书评

暂无评论

PROCEEDINGS OF THE IEEE 2020年第7期108卷 971-975页

作者： Dutt, Nikil Regazzoni, Carlo S. Rinner, Bernhard Yao, Xin Nikil Dutt (Fellow IEEE) received the Ph.D. degree from the University of Illinois at Urbana–Champaign Champaign IL USA in 1989.""He is currently a Distinguished Professor of computer science (CS) cognitive sciences and electrical engineering and computer sciences (EECS) with the University of California at Irvine Irvine CA USA. He is a coauthor of seven books. His research interests include embedded systems electronic design automation (EDA) computer architecture distributed systems healthcare Internet of Things (IoT) and brain-inspired architectures and computing.""Dr. Dutt is a Fellow of ACM. He was a recipient of the IFIP Silver Core Award. He has received numerous best paper awards. He serves as the Steering Committee Chair of the IEEE/ACM Embedded Systems Week (ESWEEK). He is also on the steering organizing and program committees of several premier EDA and embedded system design conferences and workshops. He has served on the Editorial Boards for the IEEE Transactions on Very Large Scale Integration (VLSI) Systems and the ACM Transactions on Embedded Computing Systems and also previously served as the Editor-in-Chief (EiC) for the ACM Transactions on Design Automation of Electronic Systems. He served on the Advisory Boards of the IEEE Embedded Systems Letters the ACM Special Interest Group on Embedded Systems the ACM Special Interest Group on Design Automationt and the ACM Transactions on Embedded Computing Systems. Carlo S. Regazzoni (Senior Member IEEE) received the M.S. and Ph.D. degrees in electronic and telecommunications engineering from the University of Genoa Genoa Italy in 1987 and 1992 respectively.""He is currently a Full Professor of cognitive telecommunications systems with the Department of Electrical Electronics and Telecommunication Engineering and Naval Architecture (DITEN) University of Genoa and a Co-Ordinator of the Joint Doctorate on Interactive and Cognitive Environments (JDICE) international Ph.D. course started initially as EU Erasmus Mundus Project and

Autonomous systems are able to make decisions and potentially take actions without direct human intervention, which requires some knowledge about the system and its environment as well as goal-oriented reasoning. In computer systems, one can derive such behavior from the concept of a rational agent with autonomy (“control over its own actions”), reactivity (“react to events from the environment”), proactivity (“act on its own initiative”), and sociality (“interact with other agents”) as fundamental properties \n[1]\n. Autonomous systems will undoubtedly pervade into our everyday lives, and we will find them in a variety of domains and applications including robotics, transportation, health care, communications, and entertainment to name a few. \nThe articles in this month’s special issue cover concepts and fundamentals, architectures and techniques, and applications and case studies in the exciting area of self-awareness in autonomous systems.

关键词： Special issues and sections Autonomous systems Self-aware Robot sensing systems Computational modeling

Circumventing obstacles for visual robot navigation using a stack of odometric data

学校读者我要写书评

暂无评论

Circumventing obstacles for visual robot navigation using a ...

2017 World Congress on engineering, WCE 2017

作者： Mendes, Mateus Coimbra, A. Paulo Crisóstomo, Manuel M. ESTGOH Polytechnic Institute of Coimbra Portugal ISR - Institute of Systems and Robotics Dept. of Electrical and Computer Engineering University of Coimbra Portugal

ISBN: (纸本)9789881404749

Recent advances in understanding the source of intelligent behaviour show that it is strongly supported on the use of a large and sophisticated memory. Constant increase of processing power and constant cost decrease of computer memory have encouraged research in vision-based methods for robot navigation. The present approach uses images stored into a Sparse Distributed Memory, implemented in parallel in a Graphics Processing Unit, as a method for robot localization and navigation. Algorithms for following previously learnt paths using visual and odometric information are described. A stack-based method for avoiding random obstacles, using visual information, is proposed. The results show the algorithms are adequate for indoors robot localization and navigation.

关键词： Graphics processing unit

Corrigendum to “Performance optimization of IoT based biological systems using deep learning” [computer Communications 155 (2020) 24–31]

学校读者我要写书评

暂无评论

computer Communications 2020年 160卷 863-863页

作者： Omer Irshad Muhammad Usman Ghani Khan Razi Iqbal Shakila Basheer Ali Kashif Bashir Department of Computer Science and Engineering The University of Engineering and Technology Lahore Pakistan National Center of Artificial Intelligence Al-Khawarizmi Institute of Computer Science The University of Engineering and Technology Lahore Pakistan Al-Khawarizmi Institute of Computer Science The University of Engineering and Technology Lahore Pakistan Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Manchester Metropolitan University UK School of Electrical Engineering and Computer Science National University of Science and Technology Islamabad (NUST) Pakistan

New design techniques for globally convergent simultaneous localization and mapping: Analysis and implementation

学校读者我要写书评

暂无评论

Workshop on Sensing and Control for Autonomous Vehicles: Applications to Land, Water and Air Vehicles, 2017

作者： Lourenço, Pedro Guerreiro, Bruno Batista, Pedro Oliveira, Paulo Silvestre, Carlos Laboratory for Robotics and Engineering Systems Institute for Systems and Robotics Lisbon Portugal Department of Electrical and Computer Engineering Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal Department of Mechanical Engineering Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China

ISBN: (纸本)9783319553719

This chapter presents an overview of algorithms deeply rooted in a sensor-based approach to the SLAM problem that provide global convergence guarantees and allow for the use of partially observable landmarks. The presented algorithms address the more usual range-and-bearing SLAM problem, either in 2-D using a LiDAR or in 3-D using an RGB-D camera, as well as the range-only and bearing-only SLAM problems. For each of these formulations a nonlinear system is designed, for which state and output transformations are considered together with augmented dynamics, in such a way that the underlying system structure can be regarded as linear time-varying for observability analysis and filter design purposes. This naturally allows for the design of Kalman filters with, at least, globally asymptotically stable error dynamics, for which several experimental and simulated trials are presented to highlight the performance and consistency of the obtained filters. © Springer International Publishing AG 2017.

关键词： Kalman filters

The occupation kernel method for nonlinear system identification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Rosenfeld, Joel A. Russo, Benjamin Kamalapurkar, Rushikesh Johnson, Taylor T. Department of Mathematics and Statistics University of South Florida TampaFL33620 United States Department of Mathematics Farmingdale State College FarmingdaleNY11735 United States Department of Mechanical and Aerospace Engineering Oklahoma State University StillwaterOK74078 United States Institute for Software Integrated Systems Department of Electrical Engineering and Computer Science Vanderbilt University NashvilleTN37212 United States

This manuscript presents a novel approach to nonlinear system identification leveraging densely defined Liouville operators and a new "kernel" function that represents an integration functional over a reproducing kernel Hilbert space (RKHS) dubbed an occupation kernel. The manuscript thoroughly explores the concept of occupation kernels in the contexts of RKHSs of continuous functions, and establishes Liouville operators over RKHS where several dense domains are found for specific examples of this unbounded operator. The combination of these two concepts allow for the embedding of a dynamical system into a RKHS, where function theoretic tools may be leveraged for the examination of such systems. This framework allows for trajectories of a nonlinear dynamical system to be treated as a fundamental unit of data for nonlinear system identification routine. The approach to nonlinear system identification is demonstrated to identify parameters of a dynamical system accurately, while also exhibiting a certain robustness to noise. Copyright © 2019, The Authors. All rights reserved.

关键词： Employment

Amplification of surface plasmons in graphene-black phosphorus injection laser heterostructures

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ryzhii, .V. Otsuji, .T. Ryzhii, .M. Dubinov, A.A. Aleshkin, V. Ya. Karasik, V.E. Shur, M.S. Research Institute of Electrical Communication Tohoku University Sendai980-8577 Japan Institute of Ultra High Frequency Semiconductor Electronics of Ras Moscow117105 Center for Photonics and Two-Dimensional Materials Moscow Institute of Physics Technology Dolgoprudny141700 Center for Photonics and Infrared Technology Bauman Moscow State Technical University Moscow111005 Department of Computer Science and Engineering University of Aizu Aizu-Wakamatsu965-8580 Japan Institute for Physics of Microstructures of Ras and Lobachevsky University of Nizhny Novgorod Nizhny Novgorod60395 Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY12180 United States

We propose and evaluate the heterostructure based on the graphene-layer (GL) with the lateral electron injection from the side contacts and the hole vertical injection via the black phosphorus layer (PL) (p+PL-PL-GL heterostructure). Due to a relatively small energy of the holes injected from the PL into the GL (about 100 meV, smaller than the energy of optical phonons in the GL which is about 200 meV), the hole injection can effectively cool down the two-dimensional electron-hole plasma in the GL. This simplifies the realization of the interband population inversion and the achievement of the negative dynamic conductivity in the terahertz (THz) frequency range enabling the amplification of the surface plasmon modes. The later can lead to the plasmon lasing. The conversion of the plasmons into the output radiation can be used for a new types of the THz sources. Copyright © 2019, The Authors. All rights reserved.

关键词： Phosphorus

Spin-orbit torque based physical unclonable function

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Finocchio, G. Moriyama, T. de Rose, R. Siracusano, G. Lanuzza, M. Puliafito, V. Chiappini, S. Crupi, F. Zeng, Z. Ono, T. Carpentieri, M. Department of Mathematical and Computer Sciences Physical Sciences and Earth Sciences University of Messina Messina98166 Italy Institute for Chemical Research Kyoto University Uji Kyoto611-0011 Japan Department of Computer Engineering Modeling Electronics and Systems Engineering University of Calabria RendeI-87036 Italy Department of Electric Electronic and Computer Engineering University of Catania CataniaI-95125 Italy Istituto Nazionale di Geofisica e Vulcanologia Via di Vigna Murata 605 RomaI-00143 Italy Key Laboratory of Multifunctional Nanomaterials and Smart Systems Suzhou Institute of Nano-Tech and Nano-Bionics CAS Suzhou Jiangsu215123 China Department of Electrical and Information Engineering Polytechnic of Bari Bari70125 Italy

This paper introduces the concept of spin-orbit-torque-MRAM (SOT-MRAM) based physical unclonable function (PUF). The secret of the PUF is stored into a random state of a matrix of perpendicular SOT-MRAMs. Here, we show experimentally and with micromagnetic simulations that this random state is driven by the intrinsic nonlinear dynamics of the free layer of the memory excited by the SOT. In detail, a large enough current drives the magnetization along an in-plane direction. Once the current is removed, the in-plane magnetic state becomes unstable evolving towards one of the two perpendicular stable configurations randomly. In addition, an hybrid CMOS/spintronics model is used to evaluate the electrical characteristics of a PUF realized with an array of 16×16 SOT-MRAM cells. Beyond robustness against voltage and temperature variations, hardware authentication based on this PUF scheme has additional advantages over other PUF technologies such as non-volatility (no power consumption in standby mode), reconfigurability (the secret can be rewritten), and scalability. We believe that this work is a step forward the design of spintronic devices for application in security. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic recording