Search results for " learning"

showing 10 items of 5299 documents

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

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

Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques

2012

Penicillium fungi are among the main defects that may affect the commercialization of citrus fruits. Economic losses in fruit production may become enormous if an early detection of that kind of fungi is not carried out. That early detection is usually based either on UltraViolet light carried out manually. This work presents a new approach based on hyperspectral imagery for defect segmentation. Both the physical device and the data processing (geometric corrections and band selection) are presented. Achieved results using classifiers based on Artificial Neural Networks and Decision Trees show an accuracy around 98%; it shows up the suitability of the proposed approach.

Artificial neural networkbiologyComputer sciencebusiness.industryGeneral EngineeringDecision treeHyperspectral imagingMachine learningcomputer.software_genrebiology.organism_classificationComputer Science ApplicationsArtificial IntelligenceAgriculturePenicilliumUltraviolet lightArtificial intelligencebusinesscomputerExpert Systems with Applications
researchProduct

A Multi-layer Feed Forward Neural Network Approach for Diagnosing Diabetes

2018

Diabetes is one of the worlds major health problems according to the World Health Organization. Recent surveys indicate that there is an increase in the number of diabetic patients resulting in an increase in serious complications such as heart attacks and deaths. Early diagnosis of diabetes, particularly of type 2 diabetes, is critical since it is vital for patients to get insulin treatments. However, diagnoses could be difficult especially in areas with few medical doctors. It is, therefore, a need for practical methods for the public for early detection and prevention with minimal intervention from medical professionals. A promising method for automated diagnosis is the use of artificial…

Artificial neural networkbusiness.industryComputer science02 engineering and technologyType 2 diabetes030204 cardiovascular system & hematologymedicine.diseaseMachine learningcomputer.software_genreMissing dataData set03 medical and health sciences0302 clinical medicineIntervention (counseling)Diabetes mellitus0202 electrical engineering electronic engineering information engineeringmedicineFeedforward neural network020201 artificial intelligence & image processingArtificial intelligenceMedical diagnosisbusinesscomputer2018 11th International Conference on Developments in eSystems Engineering (DeSE)
researchProduct