Search results for "Probability vector"

showing 8 items of 8 documents

Channel selection in Cognitive Radio Networks: A Switchable Bayesian Learning Automata approach

2013

We consider the problem of a user operating within a Cognitive Radio Network (CRN) which involves N channels each associated with a Primary User (PU). The problem consists of allocating a channel which, at any given time instant is not being used by a PU, to a Secondary User (SU). Within our study, we assume that a SU is allowed to perform “channel switching”, i.e., to choose an alternate channel S times (where S +1 ≤ N) if the previous choice does not lead to a channel which is vacant. The paper first presents a formal probabilistic model for the problem itself, referred to as the Formal Secondary Channel Selection (FSCS) problem, and the characteristics of the FSCS are then analyzed. Ther…

Cognitive radioTheoretical computer sciencebusiness.industryComputer scienceBayesian probabilitySampling (statistics)Statistical modelArtificial intelligenceBayesian inferencebusinessProbability vectorCommunication channelAutomaton2013 IEEE 24th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC)
researchProduct

Generalized Bayesian Pursuit: A Novel Scheme for Multi-Armed Bernoulli Bandit Problems

2011

In the last decades, a myriad of approaches to the multi-armed bandit problem have appeared in several different fields. The current top performing algorithms from the field of Learning Automata reside in the Pursuit family, while UCB-Tuned and the e-greedy class of algorithms can be seen as state-of-the-art regret minimizing algorithms. Recently, however, the Bayesian Learning Automaton (BLA) outperformed all of these, and other schemes, in a wide range of experiments. Although seemingly incompatible, in this paper we integrate the foundational learning principles motivating the design of the BLA, with the principles of the so-called Generalized Pursuit algorithm (GPST), leading to the Gen…

Learning automatabusiness.industryComputer scienceBayesian probabilityMachine learningcomputer.software_genreBayesian inferenceConjugate priorField (computer science)Probability vectorPrinciples of learningArtificial intelligenceSet (psychology)businesscomputer
researchProduct

Statistical criteria for early-stopping of support vector machines

2007

This paper proposes the use of statistical criteria for early-stopping support vector machines, both for regression and classification problems. The method basically stops the minimization of the primal functional when moments of the error signal (up to fourth order) become stationary, rather than according to a tolerance threshold of primal convergence itself. This simple strategy induces lower computational efforts and no significant differences are observed in terms of performance and sparsity.

Mathematical optimizationEarly stoppingStructured support vector machinebusiness.industryCognitive NeuroscienceMachine learningcomputer.software_genreRegressionProbability vectorComputer Science ApplicationsSupport vector machineRelevance vector machineArtificial IntelligenceConvergence (routing)MinificationArtificial intelligencebusinesscomputerMathematicsNeurocomputing
researchProduct

The Power of the “Pursuit” Learning Paradigm in the Partitioning of Data

2019

Traditional Learning Automata (LA) work with the understanding that the actions are chosen purely based on the “state” in which the machine is. This modus operandus completely ignores any estimation of the Random Environment’s (RE’s) (specified as \(\mathbb {E}\)) reward/penalty probabilities. To take these into consideration, Estimator/Pursuit LA utilize “cheap” estimates of the Environment’s reward probabilities to make them converge by an order of magnitude faster. This concept is quite simply the following: Inexpensive estimates of the reward probabilities can be used to rank the actions. Thereafter, when the action probability vector has to be updated, it is done not on the basis of th…

Mathematical optimizationTheoretical computer scienceLearning automataBasis (linear algebra)Computer scienceRank (computer programming)Object PartitioningPartitioning-based learningEstimatorLearning Automata02 engineering and technologyProbability vectorField (computer science)AutomatonRanking0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processing[INFO]Computer Science [cs]Object Migration Automaton
researchProduct

Cross-correlation and cross-power spectral density representation by complex spectral moments

2017

Abstract A new approach to provide a complete characterization of normal multivariate stochastic vector processes is presented in this paper. Such proposed method is based on the evaluation of the complex spectral moments of the processes. These quantities are strictly related to the Mellin transform and they are the generalization of the integer-order spectral moments introduced by Vanmarcke. The knowledge of the complex spectral moments permits to obtain the power spectral densities and their cross counterpart by a complex series expansions. Moreover, with just the aid of some mathematical properties the complex fractional moments permit to obtain also the correlation and cross-correlatio…

Mellin transformField (physics)Cross-correlationApplied MathematicsMechanical EngineeringCross-correlationMathematical analysisCross power spectral densitySpectral density020101 civil engineering02 engineering and technologyWhite noise01 natural sciencesProbability vectorComplex spectral moment010305 fluids & plasmas0201 civil engineeringMechanics of Materials0103 physical sciencesComplex spectral moments Mellin transform cross power spectral density cross-correlationMechanics of MaterialRepresentation (mathematics)Series expansionMellin transformMathematics
researchProduct

The Hierarchical Continuous Pursuit Learning Automation: A Novel Scheme for Environments With Large Numbers of Actions.

2019

Although the field of learning automata (LA) has made significant progress in the past four decades, the LA-based methods to tackle problems involving environments with a large number of actions is, in reality, relatively unresolved. The extension of the traditional LA to problems within this domain cannot be easily established when the number of actions is very large. This is because the dimensionality of the action probability vector is correspondingly large, and so, most components of the vector will soon have values that are smaller than the machine accuracy permits, implying that they will never be chosen . This paper presents a solution that extends the continuous pursuit paradigm to …

Theoretical computer scienceHierarchical learning automataHierarchy (mathematics)DiscretizationLearning automataComputer Networks and CommunicationsComputer scienceLarge action numbersPursuit learning automata02 engineering and technologyVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420Probability vectorLearning automataComputer Science ApplicationsAutomatonOperator (computer programming)Artificial Intelligence0202 electrical engineering electronic engineering information engineeringBenchmark (computing)Estimator-based learning automata020201 artificial intelligence & image processingVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550SoftwareCurse of dimensionalityIEEE transactions on neural networks and learning systems
researchProduct

The Hierarchical Continuous Pursuit Learning Automation for Large Numbers of Actions

2018

Part 10: Learning - Intelligence; International audience; Although the field of Learning Automata (LA) has made significant progress in the last four decades, the LA-based methods to tackle problems involving environments with a large number of actions are, in reality, relatively unresolved. The extension of the traditional LA (fixed structure, variable structure, discretized, and pursuit) to problems within this domain cannot be easily established when the number of actions is very large. This is because the dimensionality of the action probability vector is correspondingly large, and consequently, most components of the vector will, after a relatively short time, have values that are smal…

Theoretical computer scienceHierarchical learning automataHierarchy (mathematics)Learning automataComputer sciencePursuit learning automataPursuit LALearning Automata02 engineering and technologyEstimator-based LAProbability vectorField (computer science)020202 computer hardware & architectureLA with large number of actionsVariable (computer science)Operator (computer programming)Learning Automata (LA)Action (philosophy)0202 electrical engineering electronic engineering information engineeringEstimator-based learning automata[INFO]Computer Science [cs]020201 artificial intelligence & image processingHierarchical LACurse of dimensionality
researchProduct

Modal analysis for random response of MDOF systems

1990

The usefulness of the mode-superposition method of multidegrees of freedom systems excited by stochastic vector processes is here presented. The differential equations of moments of every order are written in compact form by means of the Kronecker algebra; then the method for integration of these equations is presented for both classically and non-classically damped systems, showing that the fundamental operator available for evaluating the response in the deterministic analysis is also useful for evaluating the response in the stochastic analysis.

symbols.namesakeOperator (computer programming)Computer scienceDifferential equationStochastic processModal analysisKronecker deltaRandom responsesymbolsOrder (ring theory)Applied mathematicsProbability vector
researchProduct