Search results for " Neural Network"

showing 10 items of 1232 documents

Kolmogorov Superposition Theorem and Its Application to Multivariate Function Decompositions and Image Representation

2008

International audience; In this paper, we present the problem of multivariate function decompositions into sums and compositions of monovariate functions. We recall that such a decomposition exists in the Kolmogorov's superposition theorem, and we present two of the most recent constructive algorithms of these monovariate functions. We first present the algorithm proposed by Sprecher, then the algorithm proposed by Igelnik, and we present several results of decomposition for gray level images. Our goal is to adapt and apply the superposition theorem to image processing, i.e. to decompose an image into simpler functions using Kolmogorov superpositions. We synthetise our observations, before …

[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingImage processing[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing02 engineering and technologySuperposition theorem01 natural sciences[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing[ INFO.INFO-TI ] Computer Science [cs]/Image ProcessingComputingMethodologies_SYMBOLICANDALGEBRAICMANIPULATION0202 electrical engineering electronic engineering information engineeringApplied mathematics0101 mathematics[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingMathematicsDiscrete mathematicsSignal processingArtificial neural network010102 general mathematicsApproximation algorithmSpline (mathematics)[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Kolmogorov structure function[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]020201 artificial intelligence & image processingHypercube[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing2008 IEEE International Conference on Signal Image Technology and Internet Based Systems
researchProduct

Roughness evaluation of vine leaf by image processing

2013

International audience; The study of leaf surface roughness is very important in the domain of precision spraying. It is one of the parameters that allow to reduce costs and losses of phytosanitary prod- ucts and to improve the spray accuracy. Moreover, the leaf roughness is related to adhesion mechanisms of liquid on a surface. It can be used to define leaf nature surface (hy- drophilic/hydrophobic). The main goal of this study is thus to estimate and to follow the evolution of leaf roughness using image processing and computer vision. The develop- ment and application of computer vision for measurement of surface leaf roughness using artificial neural networks will be described. The syste…

[ MATH ] Mathematics [math]0106 biological sciences0209 industrial biotechnologyScanning electron microscope[SDV]Life Sciences [q-bio]Computer Vision[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing[MATH] Mathematics [math]02 engineering and technologySurface finishLeaf roughness01 natural sciences[PHYS] Physics [physics][SPI]Engineering Sciences [physics]020901 industrial engineering & automation[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing[ SPI ] Engineering Sciences [physics]Surface roughnessComputer vision[MATH]Mathematics [math]ComputingMilieux_MISCELLANEOUS[PHYS]Physics [physics][ PHYS ] Physics [physics]Artificial neural network[STAT]Statistics [stat]Multilayer perceptron[SDE]Environmental SciencesBiological system[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingMaterials science[ STAT ] Statistics [stat][INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing[SPI] Engineering Sciences [physics]IASTEDFast Fourier transformNeural NetworkImage processingImage processing[SDV.BV]Life Sciences [q-bio]/Vegetal BiologyTexturelanguage technologies[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingPrecision agriculturebusiness.industry[STAT] Statistics [stat]Precision agricultureArtificial intelligencebusiness010606 plant biology & botany
researchProduct

Experimental and numerical enhancement of Vibrational Resonance in a neural circuit

2012

International audience; A neural circuit exactly ruled by the FitzHugh-Nagumo equations is excited by a biharmonic signal of frequencies f and F with respective amplitudes A and B. The magnitude spectrum of the circuit response is estimated at the low frequency driving f and presents a resonant behaviour versus the amplitude B of the high frequency. For the first time, it is shown experimentally that this Vibrational Resonance effect is much more pronounced when the two frequencies are multiple. This novel enhancement is also confirmed by numerical predictions. Applications of this nonlinear effect to the detection of weak stimuli are finally discussed.

[ PHYS.COND.CM-DS-NN ] Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn]02 engineering and technologyLow frequency01 natural sciencesSignalVibrational ResonanceNuclear magnetic resonance[NLIN.NLIN-PS]Nonlinear Sciences [physics]/Pattern Formation and Solitons [nlin.PS]0103 physical sciences0202 electrical engineering electronic engineering information engineeringVibrational resonance[ NLIN.NLIN-PS ] Nonlinear Sciences [physics]/Pattern Formation and Solitons [nlin.PS][PHYS.COND.CM-DS-NN]Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn]Electrical and Electronic Engineering010306 general physicsMathematicsQuantitative Biology::Neurons and Cognition020208 electrical & electronic engineering[SPI.TRON]Engineering Sciences [physics]/ElectronicsComputational physics[ SPI.TRON ] Engineering Sciences [physics]/ElectronicsNonlinear systemAmplitudeExcited stateNonlinear resonanceBiharmonic equationNonlinear dynamical systemsFitzHugh-Nagumo
researchProduct

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

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