检索结果-内蒙古大学图书馆

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Arash Vahdat Arun Mallya Ming-Yu Liu Jan Kautz NVIDIA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS models can only optimize differentiable loss functions in search, and they require an accurate differentiable approximation of non-differentiable criteria. In this work, we present UNAS, a unified framework for NAS, that encapsulates recent DNAS and RL-based approaches under one framework. Our framework brings the best of both worlds, and it enables us to search for architectures with both differentiable and non-differentiable criteria in one unified framework while maintaining a low search cost. Further, we introduce a new objective function for search based on the generalization gap that prevents the selection of architectures prone to overfitting. We present extensive experiments on the CIFAR-10, CIFAR-100 and ImageNet datasets and we perform search in two fundamentally different search spaces. We show that UNAS obtains the state-of-the-art average accuracy on all three datasets when compared to the architectures searched in the DARTS space. Moreover, we show that UNAS can find an efficient and accurate architecture in the ProxylessNAS search space, that outperforms existing MobileNetV2 based architectures. The source code is available at \url{https://***/NVlabs/unas}.

关键词： Computer architecture Search problems DNA Linear programming Task analysis Estimation Loss measurement

来源：评论

学校读者我要写书评

暂无评论

ONet – A Temporal Meta Embedding network for MOOC Dropout Prediction

ONet – A Temporal Meta Embedding Network for MOOC Dropout P...

引用

ieee International conference on Big Data

作者： Siby Charley Pulikottil Manish Gupta International Institute of Information Technology - Bangalore (IIIT-B) Bangalore India

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

While massive open online courses (MOOCs) represent a promising approach to support education for all, their effectiveness is limited by high dropout rates. Based on the analysis that dropout is deeply correlated with the interaction patterns of a user, this paper proposes an attention meta embedding based deep temporal network to predict user dropout in MOOCs. The attention meta embedding gives an attention based weighted representation of different candidate embeddings and temporal modeling is done by Bi-GRU. An experimental evaluation of our solution on the KDDCUP 2015 and XuetangX datasets shows better results (AUC and F1 score) compared to both handcrafted feature techniques and all but one of the auto feature generated techniques. We obtain comparable results to the best previous method, but without having to use different architectures for different datasets.

关键词： Measurement Computer aided instruction Electronic learning conferences Education Big Data

来源：评论

学校读者我要写书评

暂无评论

Taming Extreme Heterogeneity via Machine Learning based Design of Autonomous Manycore Systems Special Session Paper 19

Taming Extreme Heterogeneity via Machine Learning based Desi...

引用

Embedded Systems Week / Int Conf on Compilers, Architecture, and Synthesis for Embedded Systems (CASES) / International conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS) / Int Conf on Embedded Software (EMSOFT)

作者： Bogdan, Paul Chen, Fan Deshwal, Aryan Doppa, Janardhan Rao Joardar, Biresh Kumar Li, Hai (Helen) Nazarian, Shahin Song, Linghao Xiao, Yao Univ Southern Calif Los Angeles CA 90007 USA Washington State Univ Pullman WA 99164 USA Duke Univ Durham NC 27706 USA

ISBN: (纸本)9781450369237

To avoid rewriting software code for new computer architectures and to take advantage of the extreme heterogeneous processing, communication and storage technologies, there is an urgent need for determining the right amount and type of specialization while making a heterogeneous system as programmable and flexible as possible. To enable both programmability and flexibility in the heterogeneous computing era, we propose a novel complex network inspired model of computation and efficient optimization algorithms for determining the optimal degree of parallelization from old software code. This mathematical framework allows us to determine the required number and type of processing elements, the amount and type of deep memory hierarchy, and the degree of reconfiguration for the communication infrastructure, thus opening new avenues to performance and energy efficiency. Our framework enables heterogeneous manycore systems to autonomously adapt from traditional switching techniques to network coding strategies in order to sustain on-chip communication in the order of terabytes. While this new programming model enables the design of self-programmable autonomous heterogeneous manycore systems, a number of open challenges will be discussed.

关键词： Model of computation self-programming computing architectures manycore systems machine learning ReRAM processing-in-memory autonomous design optimization

来源：评论

学校读者我要写书评

暂无评论

Detection of Insider Attacks Against Interior Routing Protocols 10

Detection of Insider Attacks Against Interior Routing Protoc...

引用

10th International conference on Information and Communication Technology Convergence (ICTC) - ICT Convergence Leading the Autonomous Future

作者： Klimovski, Dragi Fox, Coen Branch, Philip Swinburne Univ Technol Fac Sci Engn & Technol Melbourne Vic Australia

ISBN: (纸本)9781728108933

Internal routing protocols are critical to the operation of private networks worldwide. Of these internal routing protocols open Shortest Path First routing protocol is the most widely used. Unfortunately, OSPF is vulnerable to insider attacks. Such attacks are reasonably straightforward to carry out by insiders but, because they are based on protocol weaknesses, very difficult to defend against. Solutions in the past have usually relied on monitoring routing tables in all routers across the network and looking for inconsistencies. This approach is cumbersome, computationally expensive and likely to result in many false positives. In this paper we present a novel technique for detecting such attacks using Recurrence Quantification Analysis (RQA). RQA is a non linear data analysis technique suitable for monitoring the behaviour of dynamic systems such as network routing. We implemented on our network testbed some of the well known but difficult t o defend against attacks. We then captured traffic t hat was generated as a result of the attacks and calculated RQA metrics based on it. Using these metrics we were able to demonstrate that RQA can be used to detect attacks quickly and with minimal computation.

关键词： Attack Detection open Shortest Path First OSPF Intrusion detection network security Core network architectures and Protocols Security network Resilience

来源：评论

学校读者我要写书评

暂无评论

Lightweight and efficient octave convolutional neural network for fire recognition 6

Lightweight and efficient octave convolutional neural networ...

引用

ieee Latin American conference on Computational Intelligence (LA-CCI)

作者： Ayala, Angel Lima, Estanislau Fernandes, Bruno Bezerra, Byron L. D. Cruz, Francisco Univ Pernambuco Escola Politecn Pernambuco Recife PE Brazil Deakin Univ Sch Informat Technol Geelong Vic Australia Univ Cent Chile Escuela Ingn Santiago Chile

ISBN: (纸本)9781728156668

Fire recognition from visual scenes is a demanding task due to the high variance of color and texture. In recent years, several fire-recognition approaches based on deep learning methods have been proposed to overcome this problem. However, building deep convolutional neural networks usually involves hundreds of layers and thousands of channels, thus requiring excessive computational cost, and a considerable amount of data. Therefore, applying deep networks in real-world scenarios remains an open challenge, especially when using devices with limitations in hardware and computing power, e.g., robots or mobile devices. To address this challenge, in this paper, we propose a lightweight and efficient octave convolutional neural network for fire recognition in visual scenes. Extensive experiments are conducted on FireSense, CairFire, FireNet, and FiSmo datasets. In overall, our architecture comprises fewer layers and fewer parameters in comparison with previously proposed architectures. Experimental results show that our model achieves higher accuracy recognition, in comparison to state-of-the-art methods, for all tested datasets.

关键词： fire recognition lightweight model octave convolution ResNet cross-dataset

来源：评论

学校读者我要写书评

暂无评论

Task Allocation of Safety-Critical Applications on Reconfigurable Multi-Core architectures with an Application on Control of Propulsion System 38

Task Allocation of Safety-Critical Applications on Reconfigu...

引用

ieee/AIAA 38th Digital Avionics Systems conference (DASC)

作者： Khamvilai, Thanakorn Sutter, Louis Mains, John B. Feron, Eric Baufreton, Philippe Neumann, Francois Krishna, Madhava Nandy, S. K. Narayan, Ranjani Haldar, Chandan Georgia Inst Technol Sch Aerosp Engn Atlanta GA 30332 USA Safran Elect & Def Massy France Indian Inst Sci CAD Lab Bangalore Karnataka India Morphing Machines Pvt Ltd Bangalore Karnataka India

ISBN: (纸本)9781728106496

In the aerospace industry, the highest criticality standard is required for the certification of avionics systems. A multi-core processor with reconfiguration capabilities where safety-critical applications are reallocated once they are affected by faults is one efficient way to enforce such criticality constraints. This paper presents a new model of a task reallocation problem for a reconfigurable multi-core architecture, which allows an execution of lower priority applications when the resources for executing the higher application are insufficient. Furthermore, it provides an implementation of an actual cyber-physical system: the control of a propulsive system with three redundant controllers. In addition to the fault injection mechanisms, a fault recovery capability and a fault detection system based on a majority rule voter are included.

关键词： multi-core reconfigurable safety-critical integer linear programming propulsion system fault tolerance voter

来源：评论

学校读者我要写书评

暂无评论

open-Source Power Outlet System for IoT-based Smart Homes

Open-Source Power Outlet System for IoT-based Smart Homes

引用

International conference on Smart Energy Systems and Technologies (SEST)

作者： Tiago Dias Pedro Sampaio Diogo Cardoso Cláudio Prates Ricardo Jesus Tiago Costa Instituto Politécnico de Lisboa (IPL) Instituto Superior de Engenharia de Lisboa (ISEL) Lisbon Portugal INESC-ID Lisbon Portugal

ISBN: (数字)9781728147017

ISBN: (纸本)9781728147024

This paper presents an open-source wireless Smart Power Outlet (SPO) system to improve the control and monitoring of household appliances in IoT-based smart homes. The system supports not only the most typical SPO functionalities, such as remote on/off control or real-time monitoring of the current consumption, but also other important functionalities, like programming of the power supply time schedule, automatic interruption of vampire currents, or prevention of electrocutions. Moreover, the devised system architecture allows to connect multiple SPOs, even with different capabilities, in an ieee 802.15.4 Sub-1 GHz Personal Area network (PAN). This network is managed by a Controller that also acts as a border router, providing remote access to the SPOs. A prof-of-concept prototype of the system has been implemented and tested. The considered SPO and Controller were based on Simple-Link Sub-1 GHz CC1310 wireless microcontrollers running the Contiki OS. The obtained results demonstrate the basic functionalities offered by the proposed open-source SPO and suggest that it can be used to make the next generation of homes smarter at lower costs.

关键词： Protocols Wireless communication Servers Communication system security open source software Smart homes ieee 802.15 Standard

来源：评论

学校读者我要写书评

暂无评论

Linear programming Approximations for Index Coding

引用

ieee TRANSACTIONS ON INFORMATION THEORY 2019年第9期65卷 5547-5564页

作者： Agarwal, Abhishek Flodin, Larkin Mazumdar, Arya Univ Massachusetts Coll Informat & Comp Sci Amherst MA 01003 USA

Index coding, a source coding problem over broadcast channels, has been a subject of both theoretical and practical interests since its introduction (by Birk and Kol, 1998). In short, the problem can be defined as follows: there is an input P (sic) (p(1), ..., p(n)), a set of n clients who each desire a single entry p(i) of the input, and a broadcaster whose goal is to send as few messages as possible to all clients so that each one can recover its desired entry. Additionally, each client has some predetermined "side information," corresponding to the certain entries of the input P, which we represent as the "side information graph" G. The graph G has a vertex v(i) for client i and a directed edge (v(i), v(j)), indicating that client i knows the jth entry of the input. Given a fixed side information graph G, we are interested in determining or approximating the "broadcast rate" of index coding on the graph, i.e., the least number of messages the broadcaster can transmit so that every client recovers its desired information. The complexity of determining this broadcast rate in the most general case is open, and the best-known approximations are barely better than the trivial O(n)-approximation corresponding to sending each client their information directly without performing any coding. Using index coding schemes based on linear programs (LPs), we take a two-pronged approach to approximating the broadcast rate. First, extending earlier work on planar graphs, we focus on approximating the broadcast rate for special graph families, such as graphs with the small chromatic number and disk graphs. In certain cases, we are able to show that simple LP-based schemes give constant-factor approximations of the broadcast rate, which seem extremely difficult to obtain in the general case. Second, we provide several LP-based schemes for the general case, which are not constant-factor approximations, but which strictly improve on the best-known schemes. These can be viewed as both

关键词： Information theory linear programming network coding approximation algorithms graph theory source coding

来源：评论

学校读者我要写书评

暂无评论

On the Maximization of Secrecy Energy Efficiency in Full-Duplex Bidirectional System With SWIPT

On the Maximization of Secrecy Energy Efficiency in Full-Dup...

引用

ieee Wireless Communications and networking conference (WCNC)

作者： Li, Meng Li, Na Wu, Huici Tao, Xiaofeng Beijing Univ Posts & Telecommun Natl Engn Lab Mobile Network Technol Beijing 100876 Peoples R China Sci & Technol Commun Networks Lab Shijiazhuang Hebei Peoples R China

ISBN: (纸本)9781538676462

This paper studies the secrecy energy efficiency (SEE) maximization problem in a full-duplex (FD) bidirectional system, where an FD base station (BS) communicates with an FD user equipment (UE) with the existence of an external user who harvests energy from the ambient radio frequency (RF) signal with SWIPT and acts as a potential eavesdropper. To balance the secrecy rate and the energy efficiency, an SEE maximization problem is formulated subject to the minimum secrecy rate, the maximum transmitted power and the minimum harvested energy. The formulated non-convex problem is solved with a two-layer optimization algorithm, where Dinkelbach method is employed to deal with the fractional programming of the outer problem and a convex approximation method based on Taylor expansion is applied to transfer the inner problem into a convex iterative program. Numerical results demonstrate the effectiveness of the proposed algorithm and the advantages of FD operation in improving SEE.

关键词： full duplex SWIPT secrecy energy efficiency artificial noise

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Reactive Power Optimization Strategy for AC/DC Hybrid Distribution network

A Two-stage Reactive Power Optimization Strategy for AC/DC H...

引用

Power and Electrical Engineering (ACPEE), 5th Asia conference on

作者： Chao Li Shihong Miao Di Zhang Lixing Li School of Electrical and Electronic Engineering Huazhong University of Science and Technology (HUST) Wuhan China

ISBN: (数字)9781728152813

ISBN: (纸本)9781728152820

To adapt to the integration of various types of distributed generations (DGs) and loads, AC/DC hybrid distribution network (ADHDN) has become an important branch of future distribution network. But the increasing penetration of DG has brought voltage regulation problem to the economic operation of ADHDN. In this paper, a two-stage reactive power optimization strategy for ADHDN based on unified power flow calculation is proposed, aiming at minimizing the comprehensive cost of ADHDN economic operation. In the first stage, the slow control measures such as open/closed status of switches in network reconfiguration and the tap position of on-load tap-changer (OLTC) transformer are determined before the day. In the second stage, the reactive power outputs of static var compensator (SVC), DG and voltage source converter (VSC) are optimized within the day. Based on second-order cone relaxation and multilayer piecewise linearization, the original mixed integer nonconvex nonlinear programming problem is transformed into a mixed integer second-order cone programming (MISOCP) problem. Finally, the modified ieee 33-node system is used for simulation calculation, and the optimal results verify the effectiveness and practicability of the proposed strategy.

关键词：

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：