Filters








76,675 Hits in 3.4 sec

Race-free interconnection networks and multiprocessor consistency

Anders Landin, Erik Hagersten, Seif Haridi
1991 Proceedings of the 18th annual international symposium on Computer architecture - ISCA '91  
We s h o w that this can be done in race-free networks without the need for a transaction to be globally performed before the next transaction can be issued.  ...  We de ne and study one class of interconnection networks, race-free networks.  ...  Heterogeneous networks A race-free network may be a part of a larger network. A simple example of this is architectures like for example the DASH 12, 5 .  ... 
doi:10.1145/115952.115964 dblp:conf/isca/LandinHH91 fatcat:defvdkjgkbh7rcld5iyrrt4frq

The RACE network architecture

B.C. Kuszmaul
Proceedings of 9th International Parallel Processing Symposium  
This paper shows how the RACE network architecture helps the RACE system by providing low cost, high-performance interconnect. (An overview of the RACE software architecture can be found in [3] .)  ...  This paper describes the architecture and implementation of the RACE system, a parallel computer for embedded applications.  ...  Acknowledgments Bob Blau, Bob Frisch, Barry Isenstein, and Craig Lund explained the RACE network architecture to the author, and corrected many errors in the manuscript.  ... 
doi:10.1109/ipps.1995.395978 dblp:conf/ipps/Kuszmaul95 fatcat:zlaajre2x5e6dejdoklfjggl7e

Towards network-wide QoE fairness using openflow-assisted adaptive video streaming

Panagiotis Georgopoulos, Yehia Elkhatib, Matthew Broadbent, Mu Mu, Nicholas Race
2013 Proceedings of the 2013 ACM SIGCOMM workshop on Future human-centric multimedia networking - FhMN '13  
The evaluation of our approach in a home networking scenario introduces user-level fairness and network stability, and illustrates the optimisation of QoE across multiple devices in a network.  ...  Many implementations naively estimate bandwidth from a one-sided client perspective, without taking into account other devices in the network.  ...  The Network Inspector monitors the packets in the network and informs the OM of the number of devices in the network, the streaming bitrate each de- vice is currently requesting and the available network  ... 
doi:10.1145/2491172.2491181 dblp:conf/sigcomm/GeorgopoulosEBM13 fatcat:7bvcw56x4zaanmz7tqhx54vaeu

Ethical Challenges in Collaborative Storytelling

Mu Mu, Mark Rouncefield, Yehia Elkhatib, Steven Simpson, Jacco Taal, Nicholas Race
2015 Proceedings of the 2015 ACM SIGCOMM Workshop on Ethics in Networked Systems Research - NS Ethics '15  
The resultant platform effectively maintains the life-cycle and dependencies of the narratives and composite user stories.  ...  form as the code of conduct.  ...  stories from reporters, while people at the Silverstone circuit normally have only the view of the race at a corner".  ... 
doi:10.1145/2793013.2793019 dblp:conf/sigcomm/MuRESTR15 fatcat:xmxlg5qu4jbjhikz673og3hke4

Improving the efficiency of neural networks with virtual training data

János Hollósi, Rudolf Krecht, Norbert Markó, Áron Ballagi
2020 Hungarian Journal of Industry and Chemistry  
One of the main tasks is to create a neural network which segments the road surface, protective barriers and other components of the racing track.  ...  In this work, the effect of computer-generated virtual images on the efficiency of different neural network architectures is examined.  ...  the framework of the New Széchenyi Plan.  ... 
doi:10.33927/hjic-2020-02 fatcat:t6s3rzevrnb33cfb3gru5gpwr4

Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents [article]

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza
2022 arXiv   pre-print
Humans race drones faster than neural networks trained for end-to-end autonomous flight. This may be related to the ability of human pilots to select task-relevant visual information effectively.  ...  This work investigates whether neural networks capable of imitating human eye gaze behavior and attention can improve neural network performance for the challenging task of vision-based autonomous drone  ...  Acknowledgments We thank Yunlong Song for help with the Flightmare simulator configuration.  ... 
arXiv:2201.02569v2 fatcat:scc33lp2ovcrdkov6uris2w7fy

Architecture Agnostic Neural Networks [article]

Sabera Talukder, Guruprasad Raghavan, Yisong Yue
2020 arXiv   pre-print
This contrast begs the question: Can we build artificial architecture agnostic neural networks? To ground this study we utilize sparse, binary neural networks that parallel the brain's circuits.  ...  In this paper, we explore an alternate method for synthesizing neural network architectures, inspired by the brain's stochastic synaptic pruning.  ...  The same procedure was applied to sparse binary networks trained to perform the car-racing imitation learning task, shown in Figure 9 .  ... 
arXiv:2011.02712v2 fatcat:wm7gml465bfefhg7f2zdtalbnu

Visual attention prediction improves performance of autonomous drone racing agents

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza, Sathishkumar V E
2022 PLoS ONE  
Humans race drones faster than neural networks trained for end-to-end autonomous flight. This may be related to the ability of human pilots to select task-relevant visual information effectively.  ...  This work investigates whether neural networks capable of imitating human eye gaze behavior and attention can improve neural networks' performance for the challenging task of vision-based autonomous drone  ...  Acknowledgments We thank Yunlong Song for help with the Flightmare simulator configuration.  ... 
doi:10.1371/journal.pone.0264471 pmid:35231038 pmcid:PMC8887736 fatcat:h2slgyjxq5bs7koyibvda4gil4

Universal Face Recognition Using Multiple Deep Learning Agent and Lazy Learning Algorithm

Kenny Vincent, Yosi Kristian
2021 CommIT Journal  
The first step in implementing this system is to develop a race classifier. The number of races is arbitrary or determined differently in a caseby-case scenario.  ...  The race classifier determines which face recognition agent will try to recognize the face in the query.  ...  NASNet-A is a product of Network Architecture Search (NAS).  ... 
doi:10.21512/commit.v15i2.6688 fatcat:3pvaeejz75hvppngxlbzs425v4

An Automated Electric Vehicle Prototype Showing New Trends in Automotive Architectures

Martin Buechel, Jelena Frtunikj, Klaus Becker, Stephan Sommer, Christian Buckl, Michael Armbruster, Andre Marek, Andreas Zirkler, Cornel Klein, Alois Knoll
2015 2015 IEEE 18th International Conference on Intelligent Transportation Systems  
To show the possibilities of modern IT systems, a demonstrator car was developed in RACE (Robust and Reliant Automotive Computing Environment for Future eCars) based on a completely redesigned E/E architecture  ...  This paper presents the architecture and components of this vehicle prototype, which is equipped with modern systems such as Steer-by-Wire without mechanical fallback.  ...  ACKNOWLEDGMENT This work is partially funded by the German Federal Ministry of Economics and Technology under grant no. 01ME12009 through the project RACE.  ... 
doi:10.1109/itsc.2015.209 dblp:conf/itsc/BuechelF0SBAMZK15 fatcat:gb375d4l25byxfjpnqen63vlfi

RACE: A Centralized Platform Computer Based Architecture for Automotive Applications

Stephan Sommer, Alexander Camek, Klaus Becker, Christian Buckl, Andreas Zirkler, Ludger Fiege, Michael Armbruster, Gernot Spiegelberg, Alois Knoll
2013 2013 IEEE International Electric Vehicle Conference (IEVC)  
One solution for these evolving systems is developed in the RACE project.  ...  AUTOSAR, the software architecture established as a standard in the automotive domain, provides no methodologies to reduce this kind of complexity and to master new challenges.  ...  ACKNOWLEDGMENTS This work is partially funded by the German Federal Ministry of Economics and Technology under grant no. 01ME12009 through the project RACE (http://www.projektrace.de/).  ... 
doi:10.1109/ievc.2013.6681152 fatcat:qawnhavb3jfqhcafdhxyef6pcq

Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction [article]

Shakti N. Wadekar, Benjamin J. Schwartz, Shyam S. Kannan, Manuel Mar, Rohan Kumar Manna, Vishnu Chellapandi, Daniel J. Gonzalez, Aly El Gamal
2021 arXiv   pre-print
speed at which the DNN can be successfully applied for predicting steering angle, (2) Neural network architecture and training methodology for learning steering and throttle without any feedback or recurrent  ...  Towards the challenge of applying end-to-end learning to autonomous racing, this paper shows results on two aspects: (1) Analyzing the relationship between the driving data used for training and the maximum  ...  We would also like to thank all members of the Purdue-USMA Indy Autonomous Challenge (IAC) Black & Gold Autonomous Racing team and the Autonomous Motorsports Purdue (AMP) student club for providing the  ... 
arXiv:2105.01799v1 fatcat:b3t6m3se4naedkolx5gtp2smcq

Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation [article]

Matthias Müller, Vincent Casser, Neil Smith, Dominik L. Michels, Bernard Ghanem
2018 arXiv   pre-print
In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation.  ...  Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient on-board processing critical for real-world deployment.  ...  This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.  ... 
arXiv:1708.05884v4 fatcat:gwpg57qlljbhnm7jnt5glxkf4q

Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation [chapter]

Matthias Müller, Vincent Casser, Neil Smith, Dominik L. Michels, Bernard Ghanem
2019 Landolt-Börnstein - Group III Condensed Matter  
In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation.  ...  Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient onboard processing critical for real-world deployment.  ...  This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.  ... 
doi:10.1007/978-3-030-11012-3_2 fatcat:6dowofvtkvc4hm6prpywvkxpse

Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI [article]

Pablo Ortega and Cedric Colas and Aldo Faisal
2018 arXiv   pre-print
Our results are comparable to those shown at the Cybathlon's BCI Race but further improvements on accuracy are required.  ...  Our preliminary results show that an efficient architecture (SmallNet), with only one convolutional layer, can classify 4 mental activities chosen by the user.  ...  Our special thanks to our Cybathlon pilot T.N. for his collaboration throughout the years and his valuable feedback. We acknowledge the financial support of the EPSRC CDT HiPEDS (Ref. No.  ... 
arXiv:1807.11752v1 fatcat:tr6bodnmnzc4bkqvqhhs2fmpte
« Previous Showing results 1 — 15 out of 76,675 results