48 Hits in 7.5 sec

A digital architecture for support vector machines: theory, algorithm, and fpga implementation

D. Anguita, A. Boni, S. Ridella
2003 IEEE Transactions on Neural Networks  
The algorithm is composed of two parts: the first one exploits a recurrent network for finding the parameters of the SVM; the second one uses a bisection process for computing the threshold.  ...  In this paper, we propose a digital architecture for support vector machine (SVM) learning and discuss its implementation on a field programmable gate array (FPGA).  ...  ACKNOWLEDGMENT The authors wish to thank two anonymous reviewers for helping to improve both the structure and the content of the paper and pointing out some imprecision in the first draft of this work  ... 
doi:10.1109/tnn.2003.816033 pmid:18244555 fatcat:due7jq5ivjdr3iyrws5kueahzm

The Vessel Schedule Recovery Problem (VSRP) – A MIP model for handling disruptions in liner shipping

Berit D. Brouer, Jakob Dirksen, David Pisinger, Christian E.M. Plum, Bo Vaaben
2013 European Journal of Operational Research  
This article focuses on the formulation of a reliable measure of profitability for the involved vehicles. The measure is based on a timespatial decomposition of customer data.  ...  -Testing the validity of the MIP approach for locating carsharing stations in one-way systems Previous research has proposed using a mixed integer programming (MIP) model for choosing the location of stations  ...  -Optimal Dynamic Tax Evasion: A Portfolio Approach Francesco Menoncin, Economics, Brescia University, Via S. Faustino, 74/B, 25122, Brescia, Italy,, Rosella Levaggi  ... 
doi:10.1016/j.ejor.2012.08.016 fatcat:c27kagfnxnhjfbil2rydhjhomm

Connectionism: past, present, and future

J. B. Pollack
1989 Artificial Intelligence Review  
Hebb set out to rectify this situation, by developing a physiologically-motivated theory of psychology.  ...  Of his own work he said: The theory is evidently a form of connectionism, one of the switchboard variety, though it does not deal in direct connections between afferent and efferent pathways: not an "S-R  ...  Then I imagined that one of my competitors, Professor Challenger, was about to solve the same problem.  ... 
doi:10.1007/bf00139193 fatcat:bkb2kdaoibhppkgtb7nkbczn5q

Neural networks for decision support:

Shimon Schocken, Gad Ariav
1994 Decision Support Systems  
In this paper, we analyze the potential contribution of neural networks for decision support, on one hand, and point out at some inherent constraints that might inhibit their use, on the other.  ...  For the sake of completeness and organization, the analysis is carried out in the context of a general-purpose DSS framework that examines all the key factors that come into play in the design of any decision  ...  An exception to this statement is the novel use of Hopfield networks in solving hard combinatorial problems (such as integer programming) [32] [36] .  ... 
doi:10.1016/0167-9236(94)90015-9 fatcat:jkmu3atnqfambjduxo5lbzuo7i

The Biointelligence Explosion [chapter]

David Pearce
2012 The Frontiers Collection  
Only a handful of genes separate Homo sapiens from our hominid ancestors on the African savannah.  ...  In the new reproductive era, hedonic set-points and intelligence alike will be ratcheted upwards in virtue of selection pressure.  ...  Any ecologically valid intelligence test designed for a species of social animal must incorporate social cognition and the capacity for co-operative problem-solving.  ... 
doi:10.1007/978-3-642-32560-1_11 fatcat:7bpjlkuwcbghlbn6djidac4mda

Fundamentals of natural computing: an overview

2007 Physics of Life Reviews  
Natural computing is a terminology introduced to encompass three classes of methods: (1) those that take inspiration from nature for the development of novel problem-solving techniques; (2) those that  ...  are based on the use of computers to synthesize natural phenomena; and (3) those that employ natural materials (e.g., molecules) to compute.  ...  . 30 Acknowledgements The author would like to thank CNPq and FAPESP for the financial support, and the reviewers for their comments and suggestions on previous versions of this manuscript.  ... 
doi:10.1016/j.plrev.2006.10.002 fatcat:n5dt75wdafbnzkfxnndv7oc56m

A two-stage heuristic for the university course timetabling problem [chapter]

Máté Pintér, Balázs Dávid
2019 StuCoSReC. Proceedings of the 2019 6th Student Computer Science Research Conference  
Published by University of Primorska Press Titov trg 4, si-6000 Koper Editor-in-Chief Jonatan Vinkler Managing Editor Alen Ježovnik Koper, 2019 isBN 978-961-7055-82-5 (pdf)  ...  Generally, the aim is to decompose a computer program into modules, which are set of smaller programs to solve sub problems. Smaller programs interact with one another in a simple, well defined way.  ...  The modified triggering model can be solved by the optimization problem in (1) (2) (3) where the maximum number of steps is set to R, and Tj is the triggering set for each vertex, being the set of all  ... 
doi:10.26493/978-961-7055-82-5.27-30 fatcat:mv36atnxqvczjg7m7aetrpvy6y

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second.  ...  Modern computation based on the von Neumann architecture is today a mature cutting-edge science.  ...  Acknowledgements The research was funded in part by C-BRIC, one of six centres in JUMP, a Semiconductor Research Corporation (SRC) program sponsored by DARPA, the National Science Foundation, the Technology  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents

David Vernon, Giorgio Metta, Giulio Sandini
2007 IEEE Transactions on Evolutionary Computation  
It does so based on a characterization of cognitive systems as systems which exhibit adaptive, anticipatory, and purposive goal-directed behavior.  ...  In each of these areas, we highlight the implications and attendant problems of adopting a developmental approach, both from phylogenetic and ontogenetic points of view.  ...  ACKNOWLEDGMENT The authors would like to acknowledge the many helpful comments of the two anonymous referees on earlier versions of this paper.  ... 
doi:10.1109/tevc.2006.890274 fatcat:s3ueaficnjbebkrfnend4ahpau

Neural blackboard architectures of combinatorial structures in cognition

Frank van der Velde, Marc de Kamps
2006 Behavioral and Brain Sciences  
In his recent book on the foundations of language, Jackendoff described four fundamental problems for a neural instantiation of combinatorial structures: the massiveness of the binding problem, the problem  ...  This paper aims to show that these problems can be solved by means of neural "blackboard" architectures. For this purpose, a neural blackboard architecture for sentence structure is presented.  ...  In any lifetime, one can form only a minute set of conjunctive representations for this set (of the order of one sentence for every 10 10 sentences or more).  ... 
doi:10.1017/s0140525x06009022 pmid:16542539 fatcat:yjti7u4gxnaojk6m6gspdasmka

Recurrent Neural Networks [chapter]

Sajid A. Marhon, Christopher J. F. Cameron, Stefan C. Kremer
2013 Intelligent Systems Reference Library  
Others address real-time solutions of optimization problems and a unified method for designing optimization neural network models with global convergence.  ...  The latter work presents evidence for a computational paradigm that has higher potential for pattern capacity and boundary flexibility than a multilayer static feedforward network.  ...  The author would like to thank Noel Sharkey, Larry Medsker, Fredrik Linåker, and Henrik Jacobsson for their useful feedback on earlier versions of the work, and Lars Niklasson for providing Figure 1 .  ... 
doi:10.1007/978-3-642-36657-4_2 fatcat:jnmgv7rlifhuncqhi5kxldepdm

Prolegomena to a Neurocomputational Architecture for Human Grammatical Encoding and Decoding

Gerard Kempen
2013 Neuroinformatics  
The paper answers both questions by providing the blueprint for a syntactic structure formation mechanism that is entirely based on prewired circuitry (except for referential processing, which relies on  ...  The design includes a neurocomputational mechanism for the treatment of an important class of grammatical movement phenomena.  ...  Acknowledgments I am very grateful to Karin Harbusch, Peter Hagoort, Karl-Magnus Petersson, the editor of this special issue, and three anonymous reviewers for extensive comments on earlier versions of  ... 
doi:10.1007/s12021-013-9191-4 pmid:23872869 fatcat:dz6pqe46pzcdnk2ij2r3xraace

Integral biomathics: A post-Newtonian view into the logos of bios

Plamen L. Simeonov
2010 Progress in Biophysics and Molecular Biology  
This work is an attempt for a state-of-the-art survey of natural and life sciences with the goal to define the scope and address the central questions of an original research program.  ...  It is focused on the phenomena of emergence, adaptive dynamics and evolution of self-assembling, self-organizing, self-maintaining and self-replicating biosynthetic systems viewed from a newly-arranged  ...  Acknowledgements: The author deeply appreciates the valuable help of Prof. Tatsuya Nomura from  ... 
doi:10.1016/j.pbiomolbio.2010.01.005 pmid:20146929 fatcat:ukagr4ftyjaqvknyjorvewxavm

Language and other complex behaviors: Unifying characteristics, computational models, neural mechanisms

Shimon Edelman
2017 Language Sciences  
A remedy for this methodological impasse is to augment Marr's three levels (problem, algorithm, and implementation) with two additional and related perspectives on the phenomenon in question, which are  ...  An analysis of the functional characteristics shared by complex sequential behaviors suggests that they all present a common overarching computational problem: dynamically controlled constrained navigation  ...  the forest is significantly more costly. 9 This is a well-known optimization problem, which is encountered, for instance, in goods distribution and shipping. 10 For a discussion of evolutionary novelty  ... 
doi:10.1016/j.langsci.2017.04.003 fatcat:kisve5cuqfb2nl42wioegqwvl4

Information processing, computation, and cognition

Gualtiero Piccinini, Andrea Scarantino
2010 Journal of biological physics (Print)  
Unlike 'digital computation,' which stands for a mathematical apparatus in search of applications, 'neural computation' is a label in search of a theory.  ...  The point is that such a theory need not rely on a previously existing and independently defined notion of computation, such as 'digital computation' or even 'analog computation' in its most straightforward  ...  Shannon was looking for an optimal solution to what he called the 'fundamental problem of communication' *38, p. 379], that is, the reproduction of messages from an information source to a destination.  ... 
doi:10.1007/s10867-010-9195-3 pmid:22210958 pmcid:PMC3006465 fatcat:n37mygozufbhxpicabbcirdxxq
« Previous Showing results 1 — 15 out of 48 results