Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








73 Hits in 6.2 sec

Savant: Automatic parallelization of a scheduling heuristic with machine learning

Frederic Pinel, Pascal Bouvry, Bernabe Dorronsoro, Samee U. Khan
2013 2013 World Congress on Nature and Biologically Inspired Computing  
This paper investigates the automatic parallelization of a heuristic for an NP-complete problem, with machine learning.  ...  The objective is to automatically design a new concurrent algorithm that finds solutions of comparable quality to the original heuristic.  ...  CONCLUSIONS This paper investigated the possibility of automatically parallelizing a heuristic for a combinatorial optimization problem.  ... 
doi:10.1109/nabic.2013.6617837 dblp:conf/nabic/PinelBDK13 fatcat:uy2fv4wreney5p6b37pc25eboe

Learning for Optimization with Virtual Savant

Renzo Massobrio
2022 Memoria Investigaciones en Ingeniería  
This article explores Virtual Savant, a paradigm that combines machine learning and parallel computing to solve optimization problems.  ...  In analogy to the Savant Syndrome, Virtual Savant extracts patterns from previously-solved instances to learn how to solve a given problem in a massively-parallel fashion.  ...  This article deals with VS, a novel paradigm that takes advantage of machine learning and parallel computing to address complex optimization problems [7] .  ... 
doi:10.36561/ing.22.4 doaj:9f24ef6eed604142906b28a2930f7665 fatcat:zxjxvt6hbjcujflkdqj63zvbfe

Virtual Savant for the Knapsack Problem: learning for automatic resource allocation
Виртуальный Эрудит для решения задачи о рюкзаке: обучение автоматическому распределению ресурсов

R. Massobrio, B. Dorronsoro Díaz, S.E. Nesmachnow Cánovas
2019 Proceedings of the Institute for System Programming of RAS  
Virtual Savant is a novel soft computing method that uses machine learning techniques to compute solutions to a given optimization problem.  ...  Virtual Savant aims at learning how to solve a given problem from the solutions computed by a reference algorithm, and its design allows taking advantage of modern parallel computing infrastructures.  ...  The work of Renzo Massobrio and Sergio Nesmachnow is partly supported by ANII and PEDECIBA, Uruguay. The work of Renzo Massobrio is partly supported by Fundación Carolina, Spain.  ... 
doi:10.15514/ispras-2019-31(2)-2 fatcat:524qt7bjyjdrpae5fee4ytrfbq

Editorial: Special Issue on «Advanced Computing: from Theory to Practice»
Предисловие к специальному выпуску «Продвинутые компьютерные методы: от теории к практике»

A.N. Tchernykh, A. Hadjali
2019 Proceedings of the Institute for System Programming of RAS  
of a novel soft computing method Virtual Savant that uses machine learning techniques to compute solutions to a given optimization problem.  ...  It learns from a reference algorithm to generate a new program that can solve the same optimization problem in a massively parallel fashion.  ... 
doi:10.15514/ispras-2019-31(2)-0 fatcat:7inmpcpc5rb2taiomnrcgwzkwi

A Survey of Evolutionary Computation for Resource Management of Processing in Cloud Computing [Review Article]

Mateusz Guzek, Pascal Bouvry, El-Ghazali Talbi
2015 IEEE Computational Intelligence Magazine  
Individuals and small organizations can benefit from using state-of-the-art services and infrastructure, while large companies are attracted by the flexibility and the speed with which they can obtain  ...  However, the environmental impact and legal aspects of cloud solutions pose additional challenges.  ...  ACKNOWLEDGMENTS This work has been partially funded by FNR and CNRS INTER/CNRS/11/03/Green@Cloud project, FNR and NCBiR INTER/IS/6466384/ISHOP project, FNR and Tri-ICT with the AFR contract no. 1315254  ... 
doi:10.1109/mci.2015.2405351 fatcat:nuxavfk5ezdzdlebbcrdawpyli

Book reports

2002 Computers and Mathematics with Applications  
The purposes of learning theory. I. Learning algorithms. 2. Kernel classifiers from a machine learning perspective. 2.1. Learning by risk minimization. 2.2.1.  ...  Adaptive margin machines. 2.5.1. Assessment of learning algorithms. 2.5.2. Leave-one-out machines. 2.5.3. Pitfalls of minimizing a leave-oneout bound. 2.5.4. Adaptive margin machines. 2.6.  ... 
doi:10.1016/s0898-1221(02)00272-9 fatcat:dlkuzp6p5nbilivckq5ezj5cbe

Eye on the Prize

Nils J. Nilsson
1995 The AI Magazine  
needed—to learn expertness in problem This shift has been encouraged by a number areas by learning problem-specific of factors, not the least of which is the alleged heuristics  ...  It is interesting to note that even McCarthy (1990) calls commonsense—with- with these general goals, the SOAR architecture out it they are idiot savants.  ... 
doi:10.1609/aimag.v16i2.1129 dblp:journals/aim/Nilsson95 fatcat:da3e5qpygzelze3le5hif5ncny

Amanuensis: The Programmer's Apprentice [article]

Thomas Dean, Maurice Chiang, Marcus Gomez, Nate Gruver, Yousef Hindy, Michelle Lam, Peter Lu, Sophia Sanchez, Rohun Saxena, Michael Smith, Lucy Wang, Catherine Wong
2018 arXiv   pre-print
Over time these savants learn cognitive strategies (domain-relevant problem solving skills) and develop intuitions (heuristics and the experience necessary for applying them) by learning from their expert  ...  This document provides an overview of the material covered in a course taught at Stanford in the spring quarter of 2018.  ...  Over time these savants learn cognitive strategies (domain-relevant problem solving skills) and develop intuitions (heuristics and the experience necessary for applying them) by learning from their expert  ... 
arXiv:1807.00082v2 fatcat:piwexqa2xvgg5ec5xwkswstswy

Entity disambiguation in anonymized graphs using graph kernels

Linus Hermansson, Tommi Kerola, Fredrik Johansson, Vinay Jethava, Devdatt Dubhashi
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
A motivating example is the name Chris Anderson, which could either refer to Chris Anderson, the curator of TED Talks, or Chris Anderson, the former editor-in-chief of WIRED Magazine.  ...  Both individuals work in overlapping fields, and deciding whom is referred to could be a difficult task, even when considering context.  ...  A word of thanks goes to Devdatt Dubhashi for providing helpful comments and curiosity in the work.  ... 
doi:10.1145/2505515.2505565 dblp:conf/cikm/HermanssonKJJD13 fatcat:vazawm2ix5b5zbw2hvkzdvzcju

Impressões dos professores em formação continuada sobre Resolução de Problemas na Educação Básica

Mara Goi
2018 Em Extensão  
. _ C C/"' { Finally, the past decade has wimessed the emergence of various automatizing devices, teaching machines, to aid in teaching.  ...  Assume a child is presented with a pinball machine which bounces a ball off a wall at an angle.  ... 
doi:10.14393/ree-v17n12018-art02 fatcat:oeovvvqfejaotldmq7vp35tsti

Effective web crawling

Carlos Castillo
2005 SIGIR Forum  
We also propose several mechanisms for server cooperation to reduce network traffic and improve the representation of a Web page in a search engine with the help of Web site managers.  ...  We start by designing a new model and architecture for a Web crawler that tightly integrates the crawler with the rest of the search engine, providing access to the metadata and links of the documents  ...  We also learned that for a good scheduling using a file with meta-data, the important search engine parameter is not the minimum re-visiting period, but the maximum acceptable outdated probability; otherwise  ... 
doi:10.1145/1067268.1067287 fatcat:kxnfz2jiifhdphoccit4rbzule

Papers read at the 26th Annual Meeting of the Psychonomic Society

1985 Bulletin of the Psychonomic Society  
Hotel Reservations A room reservation card for the hotel is enclosed with this program. Please make your room reservations promptly by returning the completed card to the hotel.  ...  Availability of our room block and the special rates are guaranteed only to those whose reservation cards are received three weeks prior to the meeting.  ...  Further studies have revealed a striking asymmetry, which suggests that search for the presence of a visual primitive is automatic and parallel, whereas search for the absence of thesame feature is serial  ... 
doi:10.3758/bf03329844 fatcat:pxwbe5wuizcybb3k5konrlfn6a

Biological Blueprints for Next Generation AI Systems [article]

Thomas Dean, Chaofei Fan, Francis E. Lewis, Megumi Sano
2019 arXiv   pre-print
With recent advances in machine learning and artificial neural networks, many neuroscientists are partnering with AI researchers and machine learning experts to analyze data and construct models.  ...  This paper attempts to demonstrate the value of such collaborations by providing examples of how insights derived from neuroscience research are helping to develop new machine learning algorithms and artificial  ...  Neural Turing Machines coupled with reinforcement learning are capable of learning simple programs [78] .  ... 
arXiv:1912.00421v1 fatcat:4drdwdgdwnf57b6b4agnzftyhe

Natural-Born Cyborgs: Minds, Technologies, and the Future of Human Intelligence (review)

Mark Erickson
2004 Canadian journal of sociology  
The cyborg, remember, was to be a human agent with some additional, machine-controlled, layers of automatic (homeostatic) functioning, allowing her to survive in alien or inhospitable environments.  ...  Instead of trying, ponderously and improbably, to rig our machines to "read our minds," we simply open a new channel and allow our brains to learn to control the machines.  ... 
doi:10.1353/cjs.2004.0038 fatcat:w4y2rzpakbcgbivjhpsbizvmzu

Genetic Programming III - Darwinian Invention and Problem Solving

Peter Nordin
1999 Evolutionary Computation  
Special thanks goes to our reviewers, who stuck with us through a major reorganization of the book and provided insightful and useful comments.  ...  Acknowledgments We would like to acknowledge the help of our editor, Denise Penrose, and that of Edward Wade and Emilia Thiuri, at Morgan Kaufmann Publishers.  ...  Other schedules, such as variable and fixed interval and ratio schedules, resulted in characteristic patterns of learning.  ... 
doi:10.1162/evco.1999.7.4.451 fatcat:27732t6mfvgt7mzpbvkrv6wcqm
« Previous Showing results 1 — 15 out of 73 results