Search results for "NEURAL NETWORK"

showing 10 items of 1385 documents

A Neural Network Meta-Model and its Application for Manufacturing

2015

International audience; Manufacturing generates a vast amount of data both from operations and simulation. Extracting appropriate information from this data can provide insights to increase a manufacturer's competitive advantage through improved sustainability, productivity, and flexibility of their operations. Manufacturers, as well as other industries, have successfully applied a promising statistical learning technique, called neural networks (NNs), to extract meaningful information from large data sets, so called big data. However, the application of NN to manufacturing problems remains limited because it involves the specialized skills of a data scientist. This paper introduces an appr…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]0209 industrial biotechnology[SPI] Engineering Sciences [physics]Computer scienceneural networkBig dataContext (language use)02 engineering and technologycomputer.software_genreMachine learningCompetitive advantageData modeling[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI][SPI]Engineering Sciences [physics]020901 industrial engineering & automationPMML0202 electrical engineering electronic engineering information engineering[ SPI ] Engineering Sciences [physics][ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI]data analyticsArtificial neural networkbusiness.industrymeta-modelMetamodelingmanufacturingAnalyticsSustainabilityPredictive Model Markup LanguageData analysis020201 artificial intelligence & image processingData miningArtificial intelligencebusinesscomputer
researchProduct

Incorporating depth information into few-shot semantic segmentation

2021

International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]Artificial neural networkComputer sciencebusiness.industry[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020206 networking & telecommunications02 engineering and technologyImage segmentationSemanticsVisualization[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI][INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingMetric (mathematics)0202 electrical engineering electronic engineering information engineeringEmbeddingRGB color modelSegmentationComputer visionArtificial intelligencebusiness
researchProduct

Research and implementation of artificial neural networks models for high velocity oxygen fuel thermal spraying

2020

In the high velocity oxygen fuel (HVOF) spray process, the coating properties are sensitive to the characteristics of in-flight particles, which are mainly determined by the process parameters. Due to the complex chemical and thermodynamic reactions during the deposition procedure, obtaining a comprehensive multi-physical model or analytical analysis of the HVOF process is still a challenging issue. This study proposes to develop a robust methodology via artificial neural networks (ANN) to solve this problem for the HVOF sprayed NiCr-Cr3C2 coatings under different operating parameters.First, 40 sets of HVOF spray experiments were conducted and the coating properties were tested for analysis…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]Cr3C2-NiCrArtificial intelligenceArtificial neural networksRéseaux de neurones artificielsHvofIntelligence artificielle[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
researchProduct

Event-Based Trajectory Prediction Using Spiking Neural Networks

2021

International audience; In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]PolynomialComputer scienceNeuroscience (miscellaneous)Neurosciences. Biological psychiatry. Neuropsychiatry02 engineering and technologyunsupervised learningSNN[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]STDP03 medical and health sciencesCellular and Molecular Neuroscience0302 clinical medicineLearning rule0202 electrical engineering electronic engineering information engineeringEvent (probability theory)Original ResearchSpiking neural networkQuantitative Biology::Neurons and Cognitionmotion selectivitybusiness.industry[SCCO.NEUR]Cognitive science/Neuroscience[SCCO.NEUR] Cognitive science/NeuroscienceProcess (computing)Pattern recognitionspiking cameraTrajectoryball trajectory predictionUnsupervised learning020201 artificial intelligence & image processingArtificial intelligencebusiness030217 neurology & neurosurgeryEfficient energy useNeuroscienceRC321-571Frontiers in Computational Neuroscience
researchProduct

Optimisation et implémentation de méthodes bio-inspirées d'extraction de caractéristiques pour la reconnaissance d'objets visuels

2016

Industry has growing needs for so-called “intelligent systems”, capable of not only ac-quire data, but also to analyse it and to make decisions accordingly. Such systems areparticularly useful for video-surveillance, in which case alarms must be raised in case ofan intrusion. For cost saving and power consumption reasons, it is better to perform thatprocess as close to the sensor as possible. To address that issue, a promising approach isto use bio-inspired frameworks, which consist in applying computational biology modelsto industrial applications. The work carried out during that thesis consisted in select-ing bio-inspired feature extraction frameworks, and to optimize them with the aim t…

[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI][INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Bio-inspiréApprentissage automatiqueIntelligence artificielle[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Descripteurs[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]EmbarquéAlgorithm-architecture matching[ INFO.INFO-BI ] Computer Science [cs]/Bioinformatics [q-bio.QM]Vision par ordinateurMachine learningRéseaux de neuronesComputer vision[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM][ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI]OptimisationsFPGANeural networks[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM]
researchProduct

High third and second order non linearities of chalcogenide glasses and fibers for compact infrared non linear devices.

2008

Due to their intrinsic nature, chalcogenide glasses present attractive nonlinearities from third and second order, with values reaching between 10 and 1000 times those of silica. We present a study of their properties and their shaping with the purpose to reach efficient devices in the near-mid infrared.

[PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics]Materials scienceOptical fiberOptical glassChalcogenideInfraredPhysics::Optics02 engineering and technologyCondensed Matter::Disordered Systems and Neural Networks01 natural scienceslaw.invention010309 opticschemistry.chemical_compoundOpticslaw0103 physical sciencesComputingMilieux_MISCELLANEOUS[CHIM.MATE] Chemical Sciences/Material chemistry[PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics][ PHYS.PHYS.PHYS-OPTICS ] Physics [physics]/Physics [physics]/Optics [physics.optics]business.industrySecond-harmonic generationOrder (ring theory)[CHIM.MATE]Chemical Sciences/Material chemistry021001 nanoscience & nanotechnologyNonlinear systemchemistry[ CHIM.MATE ] Chemical Sciences/Material chemistryOptoelectronics0210 nano-technologybusinessRefractive index
researchProduct

Nonlinear Sculpturing of Optical Pulses in Fibre Systems

2019

The interplay among the effects of dispersion, nonlinearity and gain/loss in optical fibre systems can be efficiently used to shape the pulses and manipulate and control the light dynamics and, hence, lead to different pulse-shaping regimes [1,2]. However, achieving a precise waveform with various prescribed characteristics is a complex issue that requires careful choice of the initial pulse conditions and system parameters. The general problem of optimisation towards a target operational regime in a complex multi-parameter space can be intelligently addressed by implementing machine-learning strategies. In this paper, we discuss a novel approach to the characterisation and optimisation of …

[PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics][PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics]Artificial neural networkComputer simulationComputer scienceData domain02 engineering and technology01 natural sciencesPulse shaping010309 opticsRange (mathematics)Nonlinear system020210 optoelectronics & photonicsControl theory0103 physical sciencesDispersion (optics)0202 electrical engineering electronic engineering information engineeringWaveformComputingMilieux_MISCELLANEOUS
researchProduct

The multiple facets of Cajal-Retzius neurons.

2021

ABSTRACTCajal-Retzius neurons (CRs) are among the first-born neurons in the developing cortex of reptiles, birds and mammals, including humans. The peculiarity of CRs lies in the fact they are initially embedded into the immature neuronal network before being almost completely eliminated by cell death at the end of cortical development. CRs are best known for controlling the migration of glutamatergic neurons and the formation of cortical layers through the secretion of the glycoprotein reelin. However, they have been shown to play numerous additional key roles at many steps of cortical development, spanning from patterning and sizing functional areas to synaptogenesis. The use of genetic l…

[SDV.NEU.NB]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/NeurobiologyCell Adhesion Molecules NeuronalNeurogenesisSynaptogenesisHippocampusNerve Tissue Proteins[SDV.BC.IC] Life Sciences [q-bio]/Cellular Biology/Cell Behavior [q-bio.CB]BiologyDevelopmentMolecular heterogeneityHippocampusCajal-Retzius neurons03 medical and health sciencesGlutamatergicMolecular profiling0302 clinical medicineCortex (anatomy)[SDV.BC.IC]Life Sciences [q-bio]/Cellular Biology/Cell Behavior [q-bio.CB]Biological neural networkmedicineotorhinolaryngologic diseasesAnimalsHumansReelinMolecular Biology030304 developmental biologyCerebral CortexNeurons0303 health sciencesExtracellular Matrix ProteinsCell DeathSerine Endopeptidases[SDV.NEU.NB] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology[SDV.BDD.EO] Life Sciences [q-bio]/Development Biology/Embryology and OrganogenesisReelin Proteinmedicine.anatomical_structure[SDV.BDD.EO]Life Sciences [q-bio]/Development Biology/Embryology and Organogenesisbiology.proteinCortexIdentification (biology)TranscriptomeNeuroscience030217 neurology & neurosurgerySingle-cell transcriptomicsDevelopmental BiologyDevelopment (Cambridge, England)
researchProduct

Measuring vine leaf roughness by image processing

2013

International audience; In precision spraying, spray application efficiency depends on the pesticide application method, the phytosanitary product as well as the leaf surface properties. For environmental and economic reasons, the global trend is to reduce the pesticide application rate of the few approved active substances. Under these constraints, one of the challenges is to improve the efficiency of pesticide application. Different parameters can influence on pesticide application as nozzle types, liquid viscosity and leaf surface. Specific models have been developed showing that the predominant factor for the leaf is the leaf roughness, because it is related on adhesion mechanisms of li…

[SDV] Life Sciences [q-bio][SDE] Environmental SciencesGeneralized Fourier Descriptor[SDV]Life Sciences [q-bio][SDE]Environmental SciencesNeural Network[SDV.BV]Life Sciences [q-bio]/Vegetal Biology[SDV.BV] Life Sciences [q-bio]/Vegetal Biologyleaf surface roughnessnonlinear reduction dimensionality methodstexture
researchProduct

Performances of neural networks for deriving LAI estimates from existing CYCLOPES and MODIS products

2008

International audience; This paper evaluates the performances of a neural network approach to estimate LAI from CYCLOPES and MODIS nadir normalized reflectance and LAI products. A data base was generated from these products over the BELMANIP sites during the 2001-2003 period. Data were aggregated at 3 km x 3 km, resampled at 1/16 days temporal frequency and filtered to reject outliers. VEGETATION and MODIS reflectances show very consistent values in the red, near infrared and short wave infrared bands. Neural networks were trained over part of this data base for each of the 6 MODIS biome classes to retrieve both MODIS and CYCLOPES LAI products. Results show very good performances of neural …

[SPI.OTHER]Engineering Sciences [physics]/OtherMean squared errorBiome0211 other engineering and technologiesSoil Science02 engineering and technologyNEURAL NETWORKSStandard deviationALBEDONadirComputers in Earth SciencesLeaf area indexLEA021101 geological & geomatics engineeringRemote sensingMathematicsCYCLOPESGeology04 agricultural and veterinary sciencesVegetation15. Life on landCONSISTENCY OF PRODUCTSRESEAU DE NEURONESMODISTemporal resolutionOutlier040103 agronomy & agriculture0401 agriculture forestry and fisheriesVEGETATIONLEAF AREA INDEX
researchProduct