14,176 Hits in 3.9 sec

Special issue on network-based high performance computing

H. Sarbazi-Azad, A. Shahrabi, H. Beigy
2010 Journal of Supercomputing  
Over the past decade, ever-increasing demands for greater computational power have necessitated the development of High Performance Computing (HPC) systems with high availability and reliability.  ...  They propose, based on the k-means clustering and the ID3 decision tree learning approaches in machine learning theory, a combinatorial approach for unsupervised classification of anomalous and normal  ...  The proposed scheme provides a distributed load balancing system by generating almost regular networks.  ... 
doi:10.1007/s11227-010-0423-1 fatcat:vkkuddt2rfeo7f5lntuaqhwn2e

Scholarly digital libraries at scale: introduction to the special issue on very large digital libraries

Min-Yen Kan, Dongwon Lee, Ee-Peng Lim
2008 International Journal on Digital Libraries  
Such load balancing algorithms are an essential part of the robust digital library and can be integrated within the DelosDLMS or aDORe architectures.  ...  They exploit natural language cues to locate, analyze and link and citations across the two genres within a supervised machine learning framework. Richardson et al.  ... 
doi:10.1007/s00799-008-0042-0 fatcat:jeaphgbudvfl5kzooexag43xbu

Online Unrelated Machine Load Balancing with Predictions Revisited

Shi Li, Jiayi Xian
2021 International Conference on Machine Learning  
We study the online load balancing problem with machine learned predictions, and give results that improve upon and extend those in a recent paper by Lattanzi et al. (2020).  ...  Finally, we consider the learning model introduced by Lavastida et al. ( 2020 ), and show that under the model, the two vectors can be learned efficiently with a few samples of instances.  ...  Lattanzi et al. (2020) initiated the study of online load balancing with learned predictions. Their result contains two components.  ... 
dblp:conf/icml/0001X21 fatcat:bw2twckjgnar3m3a2eabqfukii

Online and Global Network Optimization: Towards the Next-Generation of Routing Platforms [article]

Jérémie Leguay, Moez Draief, Symeon Chouvardas, Stefano Paris, Georgios S. Paschos, Lorenzo Maggi, Meiyu Qi
2016 arXiv   pre-print
From now on, cutting-edge optimization and machine learning algorithms can be used to control networks in real-time.  ...  Such algorithmic architecture, called boosting or prediction with expert advice setting, is commonly used in machine learning.  ...  We thus perform admission control with expert advice. This setting is classical in machine learning, and it is commonly called boosting algorithms.  ... 
arXiv:1602.01629v1 fatcat:jg2ljsbcabazdc2ufcfv4v6iku

A Unified Framework for Knowledge Intensive Gradient Boosting: Leveraging Human Experts for Noisy Sparse Domains

Harsha Kokel, Phillip Odom, Shuo Yang, Sriraam Natarajan
We develop a unified framework for both classification and regression settings that can both effectively and efficiently incorporate such constraints to accelerate learning to a better model.  ...  We sincerely thank the subject matter experts from Turvo Inc who provided us with valuable inputs and members of Starling Lab at UT Dallas for discussions and insights.  ...  Acknowledgements HK & SN gratefully acknowledge the support of Turvo Inc. and CwC Program Contract W911NF-15-1-0461 with the US Defense Advanced Research Projects Agency (DARPA) and the Army Research Office  ... 
doi:10.1609/aaai.v34i04.5873 fatcat:c35usk3w6nbqnlremgjtev4654

Online Optimization with Untrusted Predictions [article]

Daan Rutten, Nico Christianson, Debankur Mukherjee, Adam Wierman
2022 arXiv   pre-print
The decision maker has access to a black-box oracle, such as a machine learning model, that provides untrusted and potentially inaccurate predictions of the optimal decision in each round.  ...  To illustrate the behavior of machine-learned algorithms that enable improved performance when using perfect predictions of future net loads, we plot in Figure 1 the aggregate dispatch power planned  ...  routing [8] , load balancing [47] , video streaming [23] , and thermal management of circuits [48, 49] .  ... 
arXiv:2202.03519v1 fatcat:wwe6ed5acbg2hcz6z64bnn23qy

Designing highly flexible virtual machines: the JnJVM experience

Gaël Thomas, Nicolas Geoffray, Charles Clément, Bertil Folliot
2008 Software, Practice & Experience  
Better performances of robust JVMs are explained by their Just In Time Compiler which optimizes the code. With a better JIT, we expect similar performances.  ...  Most of all, JnJVM is compiled on the fly by the MVM when it is loaded.  ...  The JnJVM is enriched with the load balancing system which modifies the application to distribute the computation on a cluster.  ... 
doi:10.1002/spe.887 fatcat:uykjtjfjrnfetb3pdfcs4cppli

Towards trustworthy Energy Disaggregation: A review of challenges, methods and perspectives for Non-Intrusive Load Monitoring [article]

Maria Kaselimi, Eftychios Protopapadakis, Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis
2022 arXiv   pre-print
Over the years, signal processing and machine learning algorithms have been combined to achieve this.  ...  The initial interest of the scientific community to formulate and describe mathematically the NILM problem using machine learning tools has now shifted into a more practical NILM.  ...  to balance between the accuracy and robustness.  ... 
arXiv:2207.02009v1 fatcat:v2vhyovvxvcvrjawgqduabdlb4

GlobalSearchRegression.jl: \ Building bridges between Machine Learning and Econometrics in Fat-Data scenarios

2020 JuliaCon Proceedings  
The first one is to describe a novel research-project designed for building bridges between machine learning and econometric worlds (ModelSelection.jl).The second one is to introduce the main characteristics  ...  implementation While some of these characteristics are shared with R and Stata alternatives (MuMin-pdredge and GSREG, respectively), our Static Load-Balancing algorithm outperform the round-robin R scheduling  ...  Notwithstanding, increasing availability of Big and -more challenging-Fat-data, force us to go beyond pure all-subsetregression approaches and combine it with machine learning feature selection algorithms  ... 
doi:10.21105/jcon.00053 fatcat:r7l5bkhatbholampj72nmlz6vm

A Robot that Walks; Emergent Behaviors from a Carefully Evolved Network

Rodney A. Brooks
1989 Neural Computation  
Robust walking behaviors can be produced by a distributed system with very limited central coordination.  ...  This expertise is a product of evolution of the organism; it can be viewed as a very long-term form of learning which provides a structured system within which individu- als might learn more specialized  ... 
doi:10.1162/neco.1989.1.2.253 fatcat:jvqtjdcxffdvhc5hnnzlmb7ovi

Cluster I/O with River

Remzi H. Arpaci-Dusseau, Eric Anderson, Noah Treuhaft, David E. Culler, Joseph M. Hellerstein, David Patterson, Kathy Yelick
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
We have implemented a number of data-intensive applications on River, which validate our design with near-ideal pxformancc in B variety of n&uniform performance scenarios.  ...  Acknowledgements First and foremost, we would like to thank Jim Gray for all of his advice and encouragement.  ...  Tbc most tine-grained applications (those that can balance load on the level of the individual records) are the simplest to construct i,, a perfomnnce-robust manner.  ... 
doi:10.1145/301816.301823 dblp:conf/iopads/Arpaci-DusseauATCHPY99 fatcat:agexl2kxdzgnxjbqchyep4rh6u

Human Decision Making with Machine Assistance: An Experiment on Bailing and Jailing

Nina Grgic-Hlaca, Christoph Engel, Krishna P. Gummadi
2019 Social Science Research Network  
Yet in many domains it is much more plausible that the ultimate choice and responsibility remain with a human decision-maker, but that she is provided with machine advice.  ...  In the field, human decision makers sometimes have a chance, after the fact, to learn whether the machine has given good advice. In study 2, after each trial we inform participants of ground truth.  ...  Hypotheses Judges may receive machine advice simply because the legislator (or the court administration) wants to ease the case load, and get the same job done by fewer judges.  ... 
doi:10.2139/ssrn.3465622 fatcat:v2nvgp5n3rbcdfds2cswllq7mm

Machine learning application in soccer: A systematic review

Markel Rico-González, José Pino-Ortega, Amaia Méndez, Filipe Clemente, Arnold Baca
2023 Biology of Sport  
Forecasting in football INTRODUCTION Machine learning (ML) is the science that allows computers to act as humans and learn, improving their knowledge from data feed over time in an autonomous way in any  ...  Therefore, as long as the most appropriate and constantly changing data sources are used, the sport scientist may predict the future indicating some pieces of advice.  ...  Data Machine Learning Practical application from Ref.  ... 
doi:10.5114/biolsport.2023.112970 fatcat:ckb4xesvyva7zmwpwwcdk37kqq

A Mobile-Based Diet Monitoring System for Obesity Management

Bruno Vieira Resende e Silva, Milad Ghiasi Rad, Juan Cui, Megan McCabe, Kaiyue Pan
2018 Journal of Health & Medical Informatics  
In addition to using techniques in computer vision and machine learning, one unique feature of this system is the realization of real-time energy balance monitoring through metabolic network simulation  ...  Recent advances in smartphones and wearable sensor technologies have empowered automated food monitoring through food image processing and eating episode detection, with the goal to conquer drawbacks of  ...  The former usually start with a set of visual features extracted from the food image and use them to train a prediction model based on Machine Learning algorithms such as Support Vector Machine (SVM),  ... 
doi:10.4172/2157-7420.1000307 pmid:30416865 pmcid:PMC6226023 fatcat:2omkqodt4rcftidxd7j75md5le

An expert system for a local planning environment

G.J. Meester
1993 International Journal of Production Economics  
pair-wise interchange) (workload balancing), _ sorting on resource load (workload balancing), (2) For workloading: -linear programming.  ...  For work loading: -linear programming with a utilization of 95%, a heuristic with a tool capacity bound and a utilization of 95%. 5.2.2.  ... 
doi:10.1016/0925-5273(93)90112-x fatcat:zqjzrv55mnafbet7rluq52qduy
« Previous Showing results 1 — 15 out of 14,176 results