Search results for "Computer Science::Neural and Evolutionary Computation"

showing 10 items of 61 documents

BELM: Bayesian Extreme Learning Machine

2011

The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap…

Computer Networks and CommunicationsComputer scienceComputer Science::Neural and Evolutionary ComputationBayesian probabilityOverfittingMachine learningcomputer.software_genrePattern Recognition AutomatedReduction (complexity)Artificial IntelligenceComputer SimulationRadial basis functionExtreme learning machineArtificial neural networkbusiness.industryEstimation theoryBayes TheoremGeneral MedicineComputer Science ApplicationsMultilayer perceptronNeural Networks ComputerArtificial intelligencebusinesscomputerAlgorithmsSoftwareIEEE Transactions on Neural Networks
researchProduct

SIMULATING THE NUMBER OF ROMANIAN`S PUPILS AND STUDENT USING ARTIFICIAL INTELLIGENCE TECHNIQUES AND COUNTRY`S ECONOMIC ESTATE

2012

The authors present the result of a research that uses artificial neural networks in order to simulate the number of Romanian`s pupils and students (PAS), considering the country`s economic situation. The objective is to determine a better method to forecast the Romanian`s PAS considering its nonlinear behaviour. Also the ANN simulation offers an image about how inputs influence the PAS. In conclusion, the use of the ANN is considered a success and the authors determine the possibility that ANN research application be extended to other countries or even to the European zone.

Computer Science::Neural and Evolutionary ComputationRevista economica
researchProduct

A Random Neural Network for the Dynamic Multicast Problem

2004

This paper proposes a new heuristic for the dynamic version of the Steiner Tree Problem in Networks (SPN). The heuristic adopts a Random Neural Network (RNN) to improve solutions obtained by previously proposed dynamic algorithms. The Random Neural Network model is adapted to map the intrinsic features of the multicast transmission on a computer network. Exhaustive experiments are carried out to validate the proposed methodology.

Computer Science::Neural and Evolutionary Computation
researchProduct

Multilayer perceptron neural networks and radial-basis function networks as tools to forecast accumulation of deoxynivalenol in barley seeds contamin…

2011

The capacity of multi-layer perceptron artificial neural networks (MLP-ANN) and radial-basis function networks (RBFNs) to predict deoxynivalenol (DON) accumulation in barley seeds contaminated with Fusarium culmorum under different conditions has been assessed. Temperature (20-28 °C), water activity (0.94-0.98), inoculum size (7-15 mm diameter), and time were the inputs while DON concentration was the output. The dataset was used to train, validate and test many ANNs. Minimizing the mean-square error (MSE) was used to choose the optimal network. Single-layer perceptrons with low number of hidden nodes proved better than double-layer perceptrons, but the performance depended on the training …

Computer Science::Neural and Evolutionary ComputationMachine learningcomputer.software_genreTECNOLOGIA ELECTRONICAB TrichothecenesFusarium culmorumRadial basis functionFusarium culmorumMathematicsbiologyArtificial neural networkPredictive microbiologybusiness.industryHordeumFunction (mathematics)biology.organism_classificationPerceptronMicrobial growthPredictive microbiologyArtificial intelligencebusinessBiological systemcomputerLeuconostoc-mesenteroidesFood ScienceBiotechnologyMultilayer perceptron neural network
researchProduct

SSPMO: A Scatter Tabu Search Procedure for Non-Linear Multiobjective Optimization

2007

We describe the development and testing of a metaheuristic procedure, based on the scatter-search methodology, for the problem of approximating the efficient frontier of nonlinear multiobjective optimization problems with continuous variables. Recent applications of scatter search have shown its merit as a global optimization technique for single-objective problems. However, the application of scatter search to multiobjective optimization problems has not been fully explored in the literature. We test the proposed procedure on a suite of problems that have been used extensively in multiobjective optimization. Additional tests are performed on instances that are an extension of those consid…

Continuous optimizationNonlinear systemMultiobjective optimization problemMathematical optimizationComputer Science::Neural and Evolutionary ComputationMathematicsofComputing_NUMERICALANALYSISGeneral EngineeringEfficient frontierMulti-objective optimizationMetaheuristicGlobal optimizationTabu searchMathematicsINFORMS Journal on Computing
researchProduct

NP-completeness of the hamming salesman problem

1985

It is shown that the traveling salesman problem, where cities are bit strings with Hamming distances, is NP-complete.

Discrete mathematicsComputer Networks and CommunicationsApplied MathematicsComputer Science::Neural and Evolutionary ComputationHamming distanceComputer Science::Computational ComplexityTravelling salesman problemCombinatoricsHigh Energy Physics::TheoryComputational MathematicsCompleteness (order theory)Computer Science::Data Structures and AlgorithmsNP-completeBottleneck traveling salesman problemHamming codeSoftwareComputer Science::Information TheoryMathematicsBIT
researchProduct

Claws contained in all n-tournaments

1993

Abstract We prove that any claw of order n with degree d≤ 3 8 n is n-unavoidable, which means that any tournament of order n contains it as a subdigraph. A simple corollary is that any tournament has a directed Hamiltonian path.

Discrete mathematicsComputer Science::Computer Science and Game TheoryClawMathematics::CombinatoricsComputer Science::Neural and Evolutionary ComputationHamiltonian pathTheoretical Computer ScienceCombinatoricssymbols.namesakeCorollaryComputer Science::Discrete MathematicssymbolsDiscrete Mathematics and CombinatoricsTournamentMathematicsDiscrete Mathematics
researchProduct

On second maximal subgroups of Sylow subgroups of finite groups

2011

Abstract Finite groups in which the second maximal subgroups of the Sylow p -subgroups, p a fixed prime, cover or avoid the chief factors of some of its chief series are completely classified.

Discrete mathematicsp-groupAlgebra and Number TheoryComputer Science::Neural and Evolutionary ComputationMathematics::History and OverviewSylow theoremsChief seriesPhysics::History of PhysicsPrime (order theory)Physics::Popular PhysicsMathematics::Group TheoryMaximal subgroupLocally finite groupCover (algebra)MathematicsJournal of Pure and Applied Algebra
researchProduct

Training Artificial Neural Networks With Improved Particle Swarm Optimization

2020

Particle Swarm Optimization (PSO) is popular for solving complex optimization problems. However, it easily traps in local minima. Authors modify the traditional PSO algorithm by adding an extra step called PSO-Shock. The PSO-Shock algorithm initiates similar to the PSO algorithm. Once it traps in a local minimum, it is detected by counting stall generations. When stall generation accumulates to a prespecified value, particles are perturbed. This helps particles to find better solutions than the current local minimum they found. The behavior of PSO-Shock algorithm is studied using a known: Schwefel's function. With promising performance on the Schwefel's function, PSO-Shock algorithm is util…

Electricity demand forecastingMathematical optimizationArtificial neural networkComputer science020209 energyComputer Science::Neural and Evolutionary ComputationMathematicsofComputing_NUMERICALANALYSIS0202 electrical engineering electronic engineering information engineeringTraining (meteorology)Particle swarm optimization020201 artificial intelligence & image processing02 engineering and technology
researchProduct

Structural Health Monitoring Procedure for Composite Structures through the use of Artificial Neural Networks

2015

In this paper different architectures of Artificial Neural Networks (ANNs) for structural damage detection are studied. The main objective is to investigate an ANN able to detect and localize damage without any prior knowledge on its characteristics so as to serve as a real-time data processor for Structural Health Monitoring (SHM) systems. Two different architectures are studied: the standard feed-forward Multi Layer Perceptron (MLP) and the Radial Basis Function (RBF) ANNs. The training data are given, in terms of a Damage Index ℑD, properly defined using a piezoelectric sensor signal output to obtain suitable information on the damage position and dimensions. The electromechanical respon…

EngineeringArtificial neural networkBasis (linear algebra)Piezoelectric sensorbusiness.industryComputer Science::Neural and Evolutionary ComputationPattern recognitionStructural engineeringData processing systemMultilayer perceptronPharmacology (medical)Radial basis functionArtificial intelligenceStructural health monitoringbusinessBoundary element methodAerotecnica Missili & Spazio
researchProduct