Filters








20 Hits in 6.2 sec

Machine Learning for Systems

Heiner Litz, Milad Hashemi
2020 IEEE Micro  
"Enhancing Model Parallelism in Neural Architecture Search for Multidevice Systems" is another article that analyzes automatic optimization techniques for improving the performance of deep neural networks  ...  In "RELEQ: A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks," the authors describe a reinforcement learning mechanism to optimize deep neural network architectures.  ... 
doi:10.1109/mm.2020.3016551 fatcat:7lbbknjtmjamha2ek5fnc2tbem

2020 Index IEEE Transactions on Very Large Scale Integration (VLSI) Systems Vol. 28

2020 IEEE Transactions on Very Large Scale Integration (vlsi) Systems  
., Conflux-An Asynchronous Two-to-One Multiplexor for Time-Division Multiplexing and Clockless, Tokenless Readout; TVLSI Feb. 2020 503-515 Holcomb, D., see 2685-2698 Holcomb, D.E., see 1807-1820 Homayoun  ...  ., +, TVLSI Feb. 2020 433-442 Algorithm and Architecture of an Efficient MIMO Detector With Cross- Level Parallel Tree-Search.  ...  ., +, TVLSI April 2020 954-967 Computational complexity Algorithm and Architecture of an Efficient MIMO Detector With Cross-Level Parallel Tree-Search.  ... 
doi:10.1109/tvlsi.2020.3041879 fatcat:33vb2eia2jfjpog4wei4peq5ge

Device and Circuit Architectures for In‐Memory Computing

Daniele Ielmini, Giacomo Pedretti
2020 Advanced Intelligent Systems  
Finally, array architectures for computing are reviewed, including typical architectures for neural network accelerators, content addressable memory (CAM), and novel circuit topologies for general-purpose  ...  In-memory computing (IMC) appears as a promising approach to suppress the memory bottleneck and enable higher parallelism of data processing, thanks to the memory array architecture.  ...  Keywords artificial intelligence, in-memory computing, machine learning, memories, neural networks  ... 
doi:10.1002/aisy.202000040 fatcat:qo4yfcftdva2npkdltopwgqkby

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap [article]

Saeed Ahmadi
2022 arXiv   pre-print
This paper helps to identify existing trends by establishing a layered architecture along with a life cycle and an ecosystem for privacy-preserving cloud systems in addition to identifying the existing  ...  This survey paper on privacy-preserving cloud computing can help pave the way for future research in related areas.  ...  and modeling error by making use of multidevice diversity.  ... 
arXiv:2204.11120v1 fatcat:tx75pckegjgqxg6tiibptiazbi

Improving the Performance of Whale Optimization Algorithm through OpenCL-Based FPGA Accelerator

Qiangqiang Jiang, Yuanjun Guo, Zhile Yang, Zheng Wang, Dongsheng Yang, Xianyu Zhou, Shangce Gao
2020 Complexity  
The proposed framework comprises two feasible parallel models called partial parallel and all-FPGA parallel, respectively.  ...  System-on-Chip.  ...  Exploration Phase (Searching for Preys ). In addition to exploitation phase, a stochastic searching technique is also adopted to enhance the exploration in WOA.  ... 
doi:10.1155/2020/8810759 fatcat:z2yil2yb5nbbjbiiuxiwodfsni

Investigations on Performance Enhancement Measures of the Bidirectional Converter in PV–Wind Interconnected Microgrid System

Madurai Elavarasan, Ghosh, Mallick, Krishnamurthy, Saravanan
2019 Energies  
The wind and PV interconnected microgrid system was mathematically modeled for steady-state conditions. This hybrid microgrid model was simulated using the MATLAB/SIMULINK platform.  ...  The outcomes establish that the system can be kept up in a steady-state condition under the recommended control plans when the network is changed, starting with one working condition then onto the next  ...  In the proposed work for the same 3 kW system, the power factor enhancement was attained between 20% to 40%.  ... 
doi:10.3390/en12142672 fatcat:7fnrfrqj4bfmbe3gkdl7g73n6q

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence

Peng Wei, Kun Guo, Ye Li, Jue Wang, Wei Feng, Shi Jin, Ning Ge, Ying-Chang Liang
2022 IEEE Access  
This paper provides a comprehensive research review on RL-enabled MEC and offers insight for development in this area.  ...  Finally, the open challenges are discussed to provide helpful guidance for future research in RL training and learning MEC.  ...  In [171] , to solve the curseof-dimensionality problem and reduce the signal overhead, an improved neural network architecture was designed for value function approximation, including local feature summation  ... 
doi:10.1109/access.2022.3183647 fatcat:pd5z6q4innd5jl25g4r7b4nq3i

2021 Index IEEE Transactions on Instrumentation and Measurement Vol. 70

2021 IEEE Transactions on Instrumentation and Measurement  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  -that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  Zhao, P., +, TIM 2021 4002811 Automatic Attention Learning Using Neural Architecture Search for Detection of Cardiac Abnormality in 12-Lead ECG.  ... 
doi:10.1109/tim.2022.3156705 fatcat:dmqderzenrcopoyipv3v4vh4ry

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence [article]

Peng Wei, Kun Guo, Ye Li, Jue Wang, Wei Feng, Shi Jin, Ning Ge, Ying-Chang Liang
2022 arXiv   pre-print
This paper provides a comprehensive research review on RL-enabled MEC and offers insight for development in this area.  ...  Finally, the open challenges are discussed to provide helpful guidance for future research in RL training and learning MEC.  ...  In [171] , to solve the curse-ofdimensionality problem and reduce the signal overhead, an improved neural network architecture was designed for the value function approximation, including local feature  ... 
arXiv:2201.11410v4 fatcat:24igkq4kbrb2pjzwf3mf3n7qtq

SmartAuth: User-Centered Authorization for the Internet of Things

Yuan Tian, Nan Zhang, Yue-Hsun Lin, XiaoFeng Wang, Blase Ur, Xianzheng Guo, Patrick Tague
2017 USENIX Security Symposium  
Through the interface, security policies can be generated and enforced by enhancing existing platforms.  ...  device's context (e.g., a humidity sensor in a bath room) to an activity's semantics (e.g., taking a bath) using natural language processing and program analysis.  ...  Our security policy model for the smart home architecture is described in the form of a triple (E, A, T ).  ... 
dblp:conf/uss/TianZLWUGT17 fatcat:fnv5tm6wszgedknufzl63xmbvq

Experiments in Immersive Virtual Reality for Scientific Visualization

Andries van Dam, David H Laidlaw, Rosemary Michelle Simpson
2002 Computers & graphics  
This article provides a snapshot of immersive virtual reality (IVR) use for scientific visualization, in the context of the evolution of computing in general and of user interfaces in particular.  ...  Clearly, visualization by itself will not solve the problem of understanding truly large datasets that would overwhelm both display capacity and the human visual system.  ...  As always we are deeply grateful for the superb editing of Katrina Avery.  ... 
doi:10.1016/s0097-8493(02)00113-9 fatcat:cvhdqfjm35gqtpsuyt5wyw6bly

Machine Learning Parallelism Could Be Adaptive, Composable and Automated

Hao Zhang
2021
Applying parallel training systems tocomplex models adds nontrivial development overheads in addition to model prototyping, and often results in lower-than-expected performance.  ...  They enable rapid compositions of parallelization strategies for unseen models, improve parallelization performance, and simplify parallel ML programming.  ...  In this chapter, we co-develop representations and systems for dynamic neural network parallelisms.  ... 
doi:10.1184/r1/14402450 fatcat:be5w3hpokjcvplwhzqjnkz5re4

Intelligent systems and services for image and video analysis [article]

Δημήτριος Ε. Διαμαντής, University Of Thessaly, Δημήτριος Ιακωβίδης
2021
This doctoral dissertation explores intelligent systems and services for image and video analysis.  ...  The architecture is capable of extracting multi-scale image features by using blocks of parallel convolutional layers with different filter sizes.  ...  Handling the pipeline execution in a highly scalable system architecture; • Task scheduling for task parallelization.  ... 
doi:10.26253/heal.uth.13375 fatcat:4fay4wumojfndc5b6cokz2wijq

Software and Hardware Co-design for Efficient Neural Networks

Aaron Zhao, Apollo-University Of Cambridge Repository, Robert Mullins
2022
A combination of different styles of neural network compression techniques can offer multiplying gains in shrinking the memory footprints.  ...  Deep Neural Networks (DNNs) offer state-of-the-art performance in many domains but this success comes at the cost of high computational and memory resources.  ...  I felt I have been increditably lucky to have him as my PhD supervisor and will always be truely thankful to the amount of reserach freedom that he lets me to have in my PhD studies.  ... 
doi:10.17863/cam.86258 fatcat:smuvfjrmvve47cfpgooxs3tea4

Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence [article]

Peng Wei, Kun Guo, Ye Li, Jue Wang, Wei Feng, Shi Jin, Ning Ge, Ying-Chang Liang
2022
This paper provides a comprehensive research review on RL-enabled MEC and offers insight for development in this area.  ...  Finally, the open challenges are discussed to provide helpful guidance for future research in RL training and learning MEC.  ...  In [169] , to solve the curse-ofdimensionality problem and reduce the signal overhead, an improved neural network architecture was designed for the value function approximation, including local feature  ... 
doi:10.48550/arxiv.2201.11410 fatcat:5242ngqtgbhvdpcuhcygxdvsru
« Previous Showing results 1 — 15 out of 20 results