Search results for "learning"

showing 10 items of 6669 documents

Online fitted policy iteration based on extreme learning machines

2016

Reinforcement learning (RL) is a learning paradigm that can be useful in a wide variety of real-world applications. However, its applicability to complex problems remains problematic due to different causes. Particularly important among these are the high quantity of data required by the agent to learn useful policies and the poor scalability to high-dimensional problems due to the use of local approximators. This paper presents a novel RL algorithm, called online fitted policy iteration (OFPI), that steps forward in both directions. OFPI is based on a semi-batch scheme that increases the convergence speed by reusing data and enables the use of global approximators by reformulating the valu…

0209 industrial biotechnologyInformation Systems and ManagementRadial basis function networkArtificial neural networkComputer sciencebusiness.industryStability (learning theory)02 engineering and technologyMachine learningcomputer.software_genreManagement Information Systems020901 industrial engineering & automationArtificial IntelligenceBellman equation0202 electrical engineering electronic engineering information engineeringBenchmark (computing)Reinforcement learning020201 artificial intelligence & image processingArtificial intelligencebusinesscomputerSoftwareExtreme learning machineKnowledge-Based Systems
researchProduct

Bio-inspired evolutionary dynamics on complex networks under uncertain cross-inhibitory signals

2019

Given a large population of agents, each agent has three possiblechoices between option 1 or 2 or no option. The two options are equally favorable and the population has to reach consensus on one of the two options quickly and in a distributed way. The more popular an option is, the more likely it is to be chosen by uncommitted agents. Agents committed to one option can be attracted by those committed to the other option through a cross-inhibitory signal. This model originates in the context of honeybee swarms, and we generalize it to duopolistic competition and opinion dynamics. The contributions of this work include (i) the formulation of a model to explain the behavioral traits of the ho…

0209 industrial biotechnologyMathematical optimizationCollective behaviorAsymptotic stabilityComputer sciencePopulationContext (language use)02 engineering and technologyMachine learningcomputer.software_genreNetwork topologyCompetition (economics)020901 industrial engineering & automationNonlinear systems0202 electrical engineering electronic engineering information engineeringElectrical and Electronic EngineeringEvolutionary dynamicseducationAbsolute stabilityeducation.field_of_studybusiness.industry020208 electrical & electronic engineeringAgentsDeadlock (game theory)Complex networkNetwork topologiesControl and Systems EngineeringArtificial intelligencebusinessDecision makingcomputerAutomatica
researchProduct

Game Theoretic Decentralized Feedback Controls in Markov Jump Processes

2017

This paper studies a decentralized routing problem over a network, using the paradigm of mean-field games with large number of players. Building on a state-space extension technique, we turn the problem into an optimal control one for each single player. The main contribution is an explicit expression of the optimal decentralized control which guarantees the convergence both to local and to global equilibrium points. Furthermore, we study the stability of the system also in the presence of a delay which we model using an hysteresis operator. As a result of the hysteresis, we prove existence of multiple equilibrium points and analyze convergence conditions. The stability of the system is ill…

0209 industrial biotechnologyMathematical optimizationDecentralized routing policies; Hysteresis; Inverse control problem; Mean-field games; Optimal control; Control and Optimization; Management Science and Operations Research; Applied MathematicsControl and OptimizationStability (learning theory)02 engineering and technologyManagement Science and Operations ResearchMean-field games01 natural sciencesDecentralized routing policie020901 industrial engineering & automationControl theorySettore MAT/05 - Analisi MatematicaMean-field gameConvergence (routing)0101 mathematicsMean field gamesMathematicsEquilibrium pointSettore SECS-S/06 - Metodi mat. dell'economia e Scienze Attuariali e FinanziarieDecentralized routing policies; Hysteresis; Inverse control problem; Mean-field games; Optimal controlApplied MathematicsHysteresis010102 general mathematics[MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC]Optimal controlOptimal control Mean-field games Inverse control problem Decentralized routing policies HysteresisDecentralised systemOptimal control Mean-field games Inverse control problem Decentralized routing policies HysteresisExpression (mathematics)Optimal controlTheory of computationDecentralized routing policiesHysteresiInverse control problemRouting (electronic design automation)Settore MAT/09 - Ricerca Operativa
researchProduct

A Hierarchical Learning Scheme for Solving the Stochastic Point Location Problem

2012

Published version of a chapter in the book: Advanced Research in Applied Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-31087-4_78 This paper deals with the Stochastic-Point Location (SPL) problem. It presents a solution which is novel in both philosophy and strategy to all the reported related learning algorithms. The SPL problem concerns the task of a Learning Mechanism attempting to locate a point on a line. The mechanism interacts with a random environment which essentially informs it, possibly erroneously, if the unknown parameter is on the left or the right of a given point which also is the current guess. The first pioneering work […

0209 industrial biotechnologyMathematical optimizationOptimization problemBinary treeDiscretizationLearning automataComputer sciencelearning automataVDP::Technology: 500::Information and communication technology: 5500102 computer and information sciences02 engineering and technologyRandom walk01 natural sciencesdicretized learningStochastic-Point problemcontrolled Random WalkVDP::Mathematics and natural science: 400::Information and communication science: 420::Knowledge based systems: 425020901 industrial engineering & automation010201 computation theory & mathematicsLine (geometry)Convergence (routing)Point (geometry)Algorithm
researchProduct

Assembly Process Modeling Through Long Short-Term Memory

2021

This paper studies Long Short-Term Memory as a component of an adaptive assembly assistance system suggesting the next manufacturing step. The final goal is an assistive system able to help the inexperienced workers in their training stage or even experienced workers who prefer such support in their manufacturing activity. In contrast with the earlier analyzed context-based techniques, Long Short-Term Memory can be applied in unknown scenarios. The evaluation was performed on the data collected previously in an experiment with 68 participants assembling as target product a customizable modular tablet. We are interested in identifying the most accurate method of next assembly step prediction…

0209 industrial biotechnologyProcess modelingComputer sciencebusiness.industryContrast (statistics)Context (language use)02 engineering and technologyModular designMachine learningcomputer.software_genreLong short term memory020901 industrial engineering & automationComponent (UML)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinesscomputer
researchProduct

Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm

2018

Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process for determining synaptic weights of such neural networks can be computationally very expensive. In this paper we propose a new learning algorithm for learning the synaptic weights of the single hidden layer feedforward neural networks in order to reduce the learning time. We propose combining the upgraded bat algorithm with the extreme learning machine. The proposed approach reduces the number of evaluations needed to train a neural network and efficiently finds optimal input weights and the hidden biases. The proposed algorithm was tested on standard benchmark clas…

0209 industrial biotechnologyQuantitative Biology::Neurons and CognitionArtificial neural networkComputer sciencebusiness.industryData classificationProcess (computing)Approximation algorithm02 engineering and technologyMachine learningcomputer.software_genre020901 industrial engineering & automationGenetic algorithm0202 electrical engineering electronic engineering information engineeringBenchmark (computing)Feedforward neural network020201 artificial intelligence & image processingArtificial intelligencebusinesscomputerBat algorithm2018 International Joint Conference on Neural Networks (IJCNN)
researchProduct

New results on stability analysis and stabilization of time-delay continuous Markovian jump systems with partially known rates matrix

2015

Summary In this note, the problems of stability analysis and controller synthesis of Markovian jump systems with time-varying delay and partially known transition rates are investigated via an input–output approach. First, the system under consideration is transformed into an interconnected system, and new results on stochastic scaled small-gain condition for stochastic interconnected systems are established, which are crucial for the problems considered in this paper. Based on the system transformation and the stochastic scaled small-gain theorem, stochastic stability of the original system is examined via the stochastic version of the bounded realness of the transformed forward system. Th…

0209 industrial biotechnologyStochastic stabilityMechanical EngineeringGeneral Chemical EngineeringBiomedical EngineeringRegular polygonStability (learning theory)Aerospace Engineering02 engineering and technologyIndustrial and Manufacturing EngineeringMarkovian jumpMatrix (mathematics)020901 industrial engineering & automationControl and Systems EngineeringSystem transformationControl theoryBounded function0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingElectrical and Electronic EngineeringMathematicsInternational Journal of Robust and Nonlinear Control
researchProduct

Adjusted bat algorithm for tuning of support vector machine parameters

2016

Support vector machines are powerful and often used technique of supervised learning applied to classification. Quality of the constructed classifier can be improved by appropriate selection of the learning parameters. These parameters are often tuned using grid search with relatively large step. This optimization process can be done computationally more efficiently and more precisely using stochastic search metaheuristics. In this paper we propose adjusted bat algorithm for support vector machines parameter optimization and show that compared to the grid search it leads to a better classifier. We tested our approach on standard set of benchmark data sets from UCI machine learning repositor…

0209 industrial biotechnologyWake-sleep algorithmActive learning (machine learning)Computer scienceStability (learning theory)Linear classifier02 engineering and technologySemi-supervised learningcomputer.software_genreCross-validationRelevance vector machineKernel (linear algebra)020901 industrial engineering & automationLeast squares support vector machine0202 electrical engineering electronic engineering information engineeringMetaheuristicBat algorithmStructured support vector machinebusiness.industrySupervised learningOnline machine learningParticle swarm optimizationPattern recognitionPerceptronGeneralization errorSupport vector machineKernel methodComputational learning theoryMargin classifierHyperparameter optimization020201 artificial intelligence & image processingData miningArtificial intelligenceHyper-heuristicbusinesscomputer2016 IEEE Congress on Evolutionary Computation (CEC)
researchProduct

Do Randomized Algorithms Improve the Efficiency of Minimal Learning Machine?

2020

Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dat…

0209 industrial biotechnologyrandom projectionlcsh:Computer engineering. Computer hardwareComputational complexity theoryComputer scienceRandom projectionlcsh:TK7885-789502 engineering and technologyMachine learningcomputer.software_genresupervised learningapproximate algorithmsSet (abstract data type)regressioanalyysi020901 industrial engineering & automationdistance–based regressionalgoritmit0202 electrical engineering electronic engineering information engineeringordinary least–squaresbusiness.industrySupervised learningsingular value decompositionminimal learning machineMultilaterationprojektioRandomized algorithmkoneoppiminenmachine learningScalabilityFeedforward neural network020201 artificial intelligence & image processingArtificial intelligenceapproksimointibusinesscomputerMachine Learning and Knowledge Extraction
researchProduct

Using Inverse Reinforcement Learning with Real Trajectories to Get More Trustworthy Pedestrian Simulations

2020

Reinforcement learning is one of the most promising machine learning techniques to get intelligent behaviors for embodied agents in simulations. The output of the classic Temporal Difference family of Reinforcement Learning algorithms adopts the form of a value function expressed as a numeric table or a function approximator. The learned behavior is then derived using a greedy policy with respect to this value function. Nevertheless, sometimes the learned policy does not meet expectations, and the task of authoring is difficult and unsafe because the modification of one value or parameter in the learned value function has unpredictable consequences in the space of the policies it represents…

0209 industrial biotechnologyreinforcement learningComputer scienceGeneral Mathematics02 engineering and technologypedestrian simulationTask (project management)learning by demonstration020901 industrial engineering & automationAprenentatgeInformàticaBellman equation0202 electrical engineering electronic engineering information engineeringComputer Science (miscellaneous)Reinforcement learningEngineering (miscellaneous)business.industrycausal entropylcsh:MathematicsProcess (computing)020206 networking & telecommunicationsFunction (mathematics)inverse reinforcement learninglcsh:QA1-939Problem domainTable (database)Artificial intelligenceTemporal difference learningbusinessoptimizationMathematics
researchProduct