Search results for "learning"

showing 10 items of 6669 documents

Road Detection for Reinforcement Learning Based Autonomous Car

2020

Human mistakes in traffic often have terrible consequences. The long-awaited introduction of self-driving vehicles may solve many of the problems with traffic, but much research is still needed before cars are fully autonomous.In this paper, we propose a new Road Detection algorithm using online supervised learning based on a Neural Network architecture. This algorithm is designed to support a Reinforcement Learning algorithm (for example, the standard Proximal Policy Optimization or PPO) by detecting when the car is in an adverse condition. Specifically, the PPO gets a penalty whenever the virtual automobile gets stuck or drives off the road with any of its four wheels.Initial experiments …

Artificial neural networkComputer sciencebusiness.industrySupervised learningNeural network architectureReinforcement learningArtificial intelligenceReinforcement learning algorithmbusinessProceedings of the 2020 The 3rd International Conference on Information Science and System
researchProduct

Classical Training Methods

2006

This chapter reviews classical training methods for multilayer neural networks. These methods are widely used for classification and function modelling tasks. Nevertheless, they show a number of flaws or drawbacks that should be addressed in the development of such systems. They work by searching the minimum of an error function which defines the optimal behaviour of the neural network. Different standard problems are used to show the capabilities of these models; in particular, we have benchmarked the algorithms in a nonlinear classification problem and in three function modelling problems.

Artificial neural networkComputer sciencebusiness.industrymedia_common.quotation_subjectTraining methodsMachine learningcomputer.software_genreError functionDelta ruleMultilayer perceptronArtificial intelligenceNonlinear classificationbusinessFunction (engineering)computermedia_common
researchProduct

Cloud screening with combined MERIS and AATSR images

2009

This paper presents a cloud screening algorithm based on ensemble methods that exploits the combined information from both MERIS and AATSR instruments on board ENVISAT in order to improve current cloud masking products for both sensors. The first step is to analyze the synergistic use of MERIS and AATSR images in order to extract some physically-based features increasing the separability of clouds and surface. Then, several artificial neural networks are trained using different sets of input features and different sets of training samples depending on acquisition and surface conditions. Finally, outputs of the trained neural networks are combined at the decision level to construct a more ac…

Artificial neural networkContextual image classificationComputer sciencebusiness.industryRadiometryCloud computingAATSRSnowSpectroscopybusinessEnsemble learningClassifier (UML)Remote sensing2009 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images

2021

Abstract Losses of electricity production in photovoltaic systems are mainly caused by the presence of faults that affect the efficiency of the systems. The identification of any overheating in a photovoltaic module, through the thermographic non-destructive test, may be essential to maintain the correct functioning of the photovoltaic system quickly and cost-effectively, without interrupting its normal operation. This work proposes a system for the automatic classification of thermographic images using a convolutional neural network, developed via open-source libraries. To reduce image noise, various pre-processing strategies were evaluated, including normalization and homogenization of pi…

Artificial neural networkContextual image classificationRenewable Energy Sustainability and the EnvironmentComputer sciencebusiness.industry020209 energyDeep learningEnergy Engineering and Power TechnologyPattern recognitionSobel operatorAutomatic Fault recognition Convolutional Neural Network Photovoltaics TensorFlow Infrared Thermography02 engineering and technologyPerceptronConvolutional neural networkThresholdingThermographic inspectionFuel Technology020401 chemical engineeringNuclear Energy and Engineering0202 electrical engineering electronic engineering information engineeringArtificial intelligence0204 chemical engineeringbusinessEnergy Conversion and Management
researchProduct

Application of optimized artificial intelligence algorithm to evaluate the heating energy demand of non-residential buildings at European level

2019

Abstract A reliable preliminary forecast of heating energy demand of a building by using a detailed dynamic simulation software typically requires an in-depth knowledge of the thermal balance, several input data and a very skilled user. The authors will describe how to use Artificial Neural Networks to predict the demand for thermal energy linked to the winter climatization of non-residential buildings. To train the neural network it was necessary to develop an accurate energy database that represents the basis of the training of a specific Artificial Neural Networks. Data came from detailed dynamic simulations performed in the TRNSYS environment. The models were built according to the stan…

Artificial neural networkDecision support toolComputer science020209 energyReliability (computer networking)02 engineering and technologyTRNSYSStandard deviationIndustrial and Manufacturing EngineeringBuilding simulationSoftware020401 chemical engineering0202 electrical engineering electronic engineering information engineering0204 chemical engineeringElectrical and Electronic EngineeringLearning algorithmThermal balanceCivil and Structural EngineeringSettore ING-IND/11 - Fisica Tecnica AmbientaleArtificial neural networkbusiness.industryMechanical EngineeringBuilding and ConstructionIndustrial engineeringPollutionDynamic simulationGeneral EnergyHigh energy performancebusinessEnergy (signal processing)Thermal energy
researchProduct

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning

2020

Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…

Artificial neural networkEnd-to-end principlebusiness.industryComputer scienceReinforcement learningSample (statistics)Markov decision processArtificial intelligenceEmpirical evidenceTrial and errorbusinessFeature learning
researchProduct

Neural Networks with Multidimensional Cross-Entropy Loss Functions

2019

Deep neural networks have emerged as an effective machine learning tool successfully applied for many tasks, such as misinformation detection, natural language processing, image recognition, machine translation, etc. Neural networks are often applied to binary or multi-class classification problems. In these settings, cross-entropy is used as a loss function for neural network training. In this short note, we propose an extension of the concept of cross-entropy, referred to as multidimensional cross-entropy, and its application as a loss function for classification using neural networks. The presented computational experiments on a benchmark dataset suggest that the proposed approaches may …

Artificial neural networkMachine translationbusiness.industryComputer scienceBinary number02 engineering and technologyFunction (mathematics)Extension (predicate logic)010502 geochemistry & geophysicsMachine learningcomputer.software_genre01 natural sciencesComputingMethodologies_PATTERNRECOGNITIONCross entropy020401 chemical engineeringBenchmark (computing)Deep neural networksArtificial intelligence0204 chemical engineeringbusinesscomputer0105 earth and related environmental sciences
researchProduct

Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling

2005

Abstract This paper presents the use of artificial neural networks (ANNs) for surface ozone modelling. Due to the usual non-linear nature of problems in ecology, the use of ANNs has proven to be a common practice in this field. Nevertheless, few efforts have been made to acquire knowledge about the problems by analysing the useful, but often complex, input–output mapping performed by these models. In fact, researchers are not only interested in accurate methods but also in understandable models. In the present paper, we propose a methodology to extract the governing rules of trained ANN which, in turn, yields simplified models by using unbiased sensitivity and pruning techniques. Our propos…

Artificial neural networkOperations researchComputer sciencebusiness.industryEcological ModelingNon linear modelMachine learningcomputer.software_genreField (computer science)chemistry.chemical_compoundSurface ozonechemistrySensitivity (control systems)Tropospheric ozoneArtificial intelligencePruning (decision trees)businesscomputerInterpretabilityEcological Modelling
researchProduct

An Adaptive Global-Local Memetic Algorithm to Discover Resources in P2P Networks

2007

This paper proposes a neural network based approach for solving the resource discovery problem in Peer to Peer (P2P) networks and an Adaptive Global Local Memetic Algorithm (AGLMA) for performing the training of the neural network. This training is very challenging due to the large number of weights and noise caused by the dynamic neural network testing. The AGLMA is a memetic algorithm consisting of an evolutionary framework which adaptively employs two local searchers having different exploration logic and pivot rules. Furthermore, the AGLMA makes an adaptive noise compensation by means of explicit averaging on the fitness values and a dynamic population sizing which aims to follow the ne…

Artificial neural networkProcess (engineering)Computer sciencebusiness.industryComputer Science::Neural and Evolutionary ComputationComputational intelligencePeer-to-peercomputer.software_genreMachine learningSizingResource (project management)Memetic algorithmNoise (video)Artificial intelligencebusinesscomputer
researchProduct

A new method for optimal synthesis of wavelet-based neural networks suitable for identification purposes

1999

Abstract This paper deals with a new method for optimal synthesis of Wavelet-Based Neural Networks (WBNN) suitable for identification purposes. The method uses a genetic algorithm (GA) combined with a steepest descent technique and least square techniques for both optimal selection of the structure of the WBNN and its training. The method is applied for designing a predictor for a chaotic temporal series

Artificial neural networkSeries (mathematics)Computer sciencebusiness.industryMathematicsofComputing_NUMERICALANALYSISChaoticPattern recognitionMachine learningcomputer.software_genreLeast squaresIdentification (information)WaveletGenetic algorithmArtificial intelligencebusinessGradient descentcomputerSelection (genetic algorithm)IFAC Proceedings Volumes
researchProduct