Filters








267,424 Hits in 6.2 sec

Fast Forecasting Of Stock Market Prices By Using New High Speed Time Delay Neural Networks

Hazem M. El-Bakry, Nikos Mastorakis
2010 Zenodo  
Simulation results using MATLAB confirm the theoretical computations.  ...  In this paper, a new approach for fast forecasting of stock market prices is presented. Such algorithm uses new high speed time delay neural networks (HSTDNNs).  ...  D degree from University of Aizu -Japan in 2007. Currently, he is assistant professor at the Faculty of Computer Science and Information Systems -Mansoura University -Egypt.  ... 
doi:10.5281/zenodo.1330763 fatcat:ekyeuacf6fg4vhtyg3kg2rkchi

Speeding Up Distributed Machine Learning Using Codes

Kangwook Lee, Maximilian Lam, Ramtin Pedarsani, Dimitris Papailiopoulos, Kannan Ramchandran
2018 IEEE Transactions on Information Theory  
can speed up distributed matrix multiplication by a factor of n.  ...  In this work, we provide theoretical insights on how coded solutions can achieve significant gains compared to uncoded ones.  ...  In this work, we explore a new research agenda, that is driven by the question: Can codes speed up distributed machine learning?  ... 
doi:10.1109/tit.2017.2736066 fatcat:vnllavqx3vforgbrorcypq235e

Technology of Computer-assisted Technical Actions Training in Team Sports

2016 European Journal of Physical Education and Sport  
When computer-assisted training is used the content is provided in a certain order with relatively small portions (steps).  ...  Then, having mastered the groundmoves, the trainee learns to perform the second element -passing the implement to one of the fellow trainees.  ...  Computer-assisted instruction method used with training computer linear programmes is successfully applied for training practical skills in shooting and in the theoretical study of gunnery regulations  ... 
doi:10.13187/ejpe.2016.13.72 fatcat:ndbrefz5bjaprg6cozrtr6m42e

Speeding up distributed machine learning using codes

Kangwook Lee, Maximilian Lam, Ramtin Pedarsani, Dimitris Papailiopoulos, Kannan Ramchandran
2016 2016 IEEE International Symposium on Information Theory (ISIT)  
We provide theoretical insights and evidence on synthetic and OpenMPI experiments on Amazon EC2 that highlight significant gains offered by coded solutions compared to uncoded ones.  ...  We show how codes can be used to speed up two of the most basic building blocks of distributed ML algorithms: data shuffling and matrix multiplication.  ...  In this work, we explore a new research agenda, that is driven by the question: Can codes speed up distributed machine learning?  ... 
doi:10.1109/isit.2016.7541478 dblp:conf/isit/LeeLPPR16 fatcat:zrzj7v7dxrh5novlu2qsh4gj2m

Quantum Machine Learning: Benefits and Practical Examples

Frank Phillipson
2020 International Workshop on the QuANtum SoftWare Engineering & pRogramming  
A quantum computer that is useful in practice, is expected to be developed in the next few years.  ...  An important application is expected to be machine learning, where benefits are expected on run time, capacity and learning efficiency.  ...  However, this exponential speed-up is not obvious and the assumptions made to come to this theoretical speed-up have some huge technological challenges, see also [9] .  ... 
dblp:conf/quanswer/Phillipson20 fatcat:d5kdtqlhajfopomcwkhan6urke

The Singularity May Be Near

Roman Yampolskiy
2018 Information  
In this paper, we provide analysis of each one of his arguments and arrive at similar conclusions, but with more weight given to the "likely to happen" prediction.  ...  Toby Walsh in "The Singularity May Never Be Near" gives six arguments to support his point of view that technological singularity may happen, but that it is unlikely.  ...  in the paper much stronger.  ... 
doi:10.3390/info9080190 fatcat:ev4l3qkkbba6rmu6dvvvbfe7wq

Barriers and facilitators of using mobile devices as an educational tool by nursing students: a qualitative research

Nasrin Nikpeyma, Mitra Zolfaghari, Aeen Mohammadi
2021 BMC Nursing  
Methods This qualitative descriptive study was conducted in 2020 on undergraduate nursing students of the Nursing and Midwifery Faculty, Tehran University of Medical Sciences.  ...  Background Although the use of mobile devices can facilitate the learning process, there may be barriers to using them for learning purposes.  ...  Acknowledgments The researchers thank all the nursing students participating in this study. Authors' contributions Study conception and design: N. N, M. Z, A.M. Data collection: N.N.  ... 
doi:10.1186/s12912-021-00750-9 pmid:34753476 pmcid:PMC8579623 fatcat:oz6bmpl6jbdqvkr5nd5vmkylla

Procrustean decomposition for orthogonal cascade detection

Kun Duan, Wei Wang, Ting Yu
2016 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this paper, our goal is to speed up a standard sliding window detector while maintaining detection accuracies.  ...  We conduct extensive experiments using our approach on two wellknown object detection datasets: INRIA pedestrian detection dataset and PASCAL VOC 2007 detection dataset.  ...  PCA or sparse coding) on complicated features [15, 28] . However, these methods introduce extra computational expense, and in practice the speed-up is not significant.  ... 
doi:10.1109/wacv.2016.7477567 dblp:conf/wacv/DuanWY16 fatcat:aqzmcjhoojaxjjvw7fwivrjwsy

A machine learning approach for grain crop's seed classification in purifying separation

A V Vlasov, A S Fadeev
2017 Journal of Physics, Conference Series  
The paper presents a study of the machine learning ability to classify seeds of a grain crop in order to improve purification processing.  ...  A set of tests is provided to show the effectiveness of the machine learning for the stated task. The ability to improve the approach with deep learning in further research is described.  ...  The method is available in the Matlab toolbox (the version used is R2016a) which is based on common feature extraction techniques include Histogram of Oriented Gradients (HOG), Speeded Up Robust Features  ... 
doi:10.1088/1742-6596/803/1/012177 fatcat:lowf2ihfyjhmhcgljm6hfhesey

Integrating Fast Karnough Map And Modular Neural Networks For Simplification And Realization Of Complex Boolean Functions

Hazem M. El-Bakry
2011 Zenodo  
Simulation results using MATLAB confirm the theoretical computations. Furthermore, a powerful solution for realization of complex functions is given.  ...  The search operation relies on performing cross correlation in the frequency domain rather than time one.  ...  and Information Engineering Vol:5, No:8, 2011 892 TABLE I THE I THEORETICAL SPEED UP RATIO FOR KARNOUGH MAPS WITH DIFFERENT SIZES TABLE II PRACTICAL SPEED UP RATIO FOR KARNOUGH MAPS WITH DIFFERENT  ... 
doi:10.5281/zenodo.1084206 fatcat:abagcv3ddzgzdhnbs6cw6swit4

Integrating Fast Karnough Map And Modular Neural Networks For Simplification And Realization Of Complex Boolean Functions

Hazem M. El-Bakry
2011 Zenodo  
Simulation results using MATLAB confirm the theoretical computations. Furthermore, a powerful solution for realization of complex functions is given.  ...  The search operation relies on performing cross correlation in the frequency domain rather than time one.  ...  and Information Engineering Vol:5, No:3, 2011 313 TABLE I THE I THEORETICAL SPEED UP RATIO FOR KARNOUGH MAPS WITH DIFFERENT SIZES TABLE II PRACTICAL SPEED UP RATIO FOR KARNOUGH MAPS WITH DIFFERENT  ... 
doi:10.5281/zenodo.1074547 fatcat:qwy5tqeu4zczpecj56dic6fuei

Complexity Bounds for Batch Active Learning in Classification [chapter]

Philippe Rolet, Olivier Teytaud
2010 Lecture Notes in Computer Science  
Roughly speaking, the speed-up is asymptotically logarithmic in the batch size λ (i.e. when λ → ∞).  ...  Practically speaking, this means that parallelizing computations on an expensive-to-label problem which is suited to active learning is very beneficial until V simultaneous queries, and less interesting  ...  Further, we are not aware of any theoretical study of the speed-up of batch Active Learning over sequential Active Learning, in terms of sample complexity bounds (speed-up is in terms of gain with respect  ... 
doi:10.1007/978-3-642-15939-8_19 fatcat:ydt3v5kjpjejveqckdkwudc2dm

Working Memory, Processing Speed, and Executive Memory Contributions to Computer-Assisted Second Language Learning

Keith E. Nelson, Aran Barlieb, Kiren Khan, Elisabeth M. Vance Trup, Mikael Heimann, Tomas Tjus, Mary Rudner, Jerker Ronnberg
2012 Contemporary Educational Technology  
How individual differences in information processing affect second language (L2) learning has been unclear in prior research.  ...  In contrast, results at demanding long-term retrieval on a posttest were more complex and revealed several dynamic relationships between processing speed, working memory, and Swedish language learning.  ...  Acknowledgments This research was supported in part by grants from the Schreyer Honors College and the College of Liberal Arts at Penn State University.  ... 
doi:10.30935/cedtech/6077 fatcat:axpdkyrclrhodo6hbrz3k5ducq

Internet as an Instrument to Transmit Theoretical Knowledge

Svetlana Kvesko, Svetlana Kvesko, Nataliya Kabanova, Daria Shamrova, A.V. Yurchenko, V.I. Syryamkin
2016 MATEC Web of Conferences  
The problem of transmitting theoretical knowledge and the role of the Internet in it require the solution due to the existing modernization of theoretical knowledge transmission process.  ...  The objective of this research is to define the role of the Internet in transmitting theoretical knowledge as it is the extremely important resource of the modern society.  ...  Acknowledgment This research is carried out under the scope "Organization and methodic issues of training specialists in Information and Measurement Technologies and Technique".  ... 
doi:10.1051/matecconf/20167901062 fatcat:ga63zyzmbvh5foyyln4llnkbpq

Feature Selection with Limited Bit Depth Mutual Information for Embedded Systems

Laura Morán-Fernández, Verónica Bolón-Canedo, Amparo Alonso-Betanzos
2018 Proceedings (MDPI)  
With the variety, speed and volume of data flowing through networks and databases, newer approaches based on machine learning are required. But what is really big in Big Data?  ...  In this work, we consider mutual informationone of the most common measures of dependence used in feature selection algorithms—with reduced precision parameters.  ...  Acknowledgments: This research has been financially supported in part by the Spanish Ministerio de Economía y Competitividad (research project TIN2015-65069-C2-1-R), by European Union FEDER funds and by  ... 
doi:10.3390/proceedings2181187 fatcat:nsuv2xedkjbhlfq37xmbbshbpm
« Previous Showing results 1 — 15 out of 267,424 results