Search results for "NEURAL NETWORK"

showing 10 items of 1385 documents

Data-based modeling of vehicle collisions by nonlinear autoregressive model and feedforward neural network

2013

Vehicle crash test is the most direct and common method to assess vehicle crashworthiness. Visual inspection and obtained measurements, such as car acceleration, are used, e.g. to examine impact severity of an occupant or to assess overall car safety. However, those experiments are complex, time-consuming, and expensive. We propose a method to reproduce car kinematics during a collision using nonlinear autoregressive (NAR) model which parameters are estimated by the use of feedforward neural network. NAR model presented in this study is derived from the more general one - nonlinear autoregressive with moving average (NARMA). Suitability of autoregressive systems for data-based modeling was …

Nonlinear autoregressive exogenous modelInformation Systems and ManagementArtificial neural networkComputer scienceCrash testComputer Science ApplicationsTheoretical Computer ScienceAccelerationAutoregressive modelArtificial IntelligenceControl and Systems EngineeringMoving averageCrashworthinessFeedforward neural networkVehicle accelerationSoftwareSimulationInformation Sciences
researchProduct

Advances in photonic reservoir computing

2017

We review a novel paradigm that has emerged in analogue neuromorphic optical computing. The goal is to implement a reservoir computer in optics, where information is encoded in the intensity and phase of the optical field. Reservoir computing is a bio-inspired approach especially suited for processing time-dependent information. The reservoir’s complex and high-dimensional transient response to the input signal is capable of universal computation. The reservoir does not need to be trained, which makes it very well suited for optics. As such, much of the promise of photonic reservoirs lies in their minimal hardware requirements, a tremendous advantage over other hardware-intensive neural net…

Nonlinear opticsQC1-99942.55.pxAnalogue computingMathematicsofComputing_NUMERICALANALYSISOptical computing05.45.-a02 engineering and technologyEuropean Social Fund01 natural sciences020210 optoelectronics & photonics42.79.ta0103 physical sciences0202 electrical engineering electronic engineering information engineeringOptical computing07.05.mh85.60.-qElectrical and Electronic Engineering010306 general physics[PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics]Artificial neural networksPhysicsnonlinear opticsReservoir computing42.79.hpanalogue computingAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic Materials42.65.-kEngineering managementWork (electrical)Research counciloptical computingScience policy42.82.-martificial neural networksBiotechnologyNanophotonics
researchProduct

Exponential synchronization of master-slave neural networks with time-delays

2009

This paper establishes an exponential H ∞ synchronization method for a class of master and slave neural networks (MSNNs) with mixed time-delays, where the delays comprise different neutral, discrete and distributed time-delays and the class covers the Lipschitz-type nonlinearity case. By introducing a novel discretized Lyapunov-Krasovskii functional in order to minimize the conservatism in the stability problem of the system and also using some free weighting matrices, new delay-dependent sufficient conditions are derived for designing a delayed state-feedback control as a synchronization law in terms of linear matrix inequalities (LMIs). The controller guarantees the exponential H ∞ synchr…

Nonlinear systemArtificial neural networkDiscretizationControl and Systems EngineeringControl theorySynchronization (computer science)Master/slaveMathematicsWeightingExponential function2009 European Control Conference (ECC)
researchProduct

Parameters identification of induction motor dynamic model for offshore applications

2014

The paper presents a technique to identify parameters of the LuGre dynamic friction model applied to represent mechanical losses of an induction motor. This method is based on Artificial Neural Networks (ANNs) system identification which is able to estimate parameters of nonlinear mathematical models. Within the presented approach, the network is first trained to associate model parameters with predicted friction torque, being given the reference motor speed. When this process completes, the inverse operation is performed and the network delivers estimated parameters of the model based on the reference friction torque. These parameters are then integrated with the dynamic model of the induc…

Nonlinear systemEngineeringDirect torque controlArtificial neural networkMathematical modelbusiness.industryControl theoryProcess (computing)System identificationControl engineeringbusinessInduction motorFriction torque2014 IEEE/ASME 10th International Conference on Mechatronic and Embedded Systems and Applications (MESA)
researchProduct

A taxonomy for wavelet neural networks applied to nonlinear modelling

2008

This article presents a novel classification of wavelet neural networks based on the orthogonality/non-orthogonality of neurons and the type of nonlinearity employed. On the basis of this classification different network types are studied and their characteristics illustrated by means of simple one-dimensional nonlinear examples. For multidimensional problems, which are affected by the curse of dimensionality, the idea of spherical wavelet functions is considered. The behaviour of these networks is also studied for modelling of a low-dimension map.

Nonlinear systemWaveletOrthogonalityArtificial neural networkBasis (linear algebra)Control and Systems EngineeringTaxonomy (general)Nonlinear modellingAlgorithmComputer Science ApplicationsTheoretical Computer ScienceMathematicsCurse of dimensionalityInternational Journal of Systems Science
researchProduct

A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification

2020

Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their a…

Normalization (statistics)General Computer ScienceComputer scienceFeature extractionESC02 engineering and technologycomputer.software_genreResidualConvolutional neural networkconvolutional neural networks0202 electrical engineering electronic engineering information engineeringGeneral Materials Scienceurbansound8kAudio signal processingBlock (data storage)Contextual image classificationGeneral EngineeringAudio classification020206 networking & telecommunications113 Computer and information sciences020201 artificial intelligence & image processinglcsh:Electrical engineering. Electronics. Nuclear engineeringData mininglcsh:TK1-9971computerresidual learningIEEE Access
researchProduct

Visual information flow in Wilson-Cowan networks.

2020

In this paper, we study the communication efficiency of a psychophysically tuned cascade of Wilson-Cowan and divisive normalization layers that simulate the retina-V1 pathway. This is the first analysis of Wilson-Cowan networks in terms of multivariate total correlation. The parameters of the cortical model have been derived through the relation between the steady state of the Wilson-Cowan model and the divisive normalization model. The communication efficiency has been analyzed in two ways: First, we provide an analytical expression for the reduction of the total correlation among the responses of a V1-like population after the application of the Wilson-Cowan interaction. Second, we empiri…

Normalization (statistics)PhysiologyComputer scienceComputationPopulationModels Biological050105 experimental psychologyRetina03 medical and health sciencesWilson–Cowan equations0302 clinical medicineMulti-informationtotal correlationHumans0501 psychology and cognitive sciencesVisual PathwaysEfficient coding hypothesisEfficient representation principleeducationVisual Cortexeducation.field_of_studyNormalization modelGeneral Neuroscience05 social sciencesUnivariateFOS: Biological sciencesQuantitative Biology - Neurons and CognitionDivisive normalizationVisual PerceptionNeurons and Cognition (q-bio.NC)Total correlationNeural Networks ComputerNerve NetAlgorithm030217 neurology & neurosurgeryImage compressionJournal of neurophysiology
researchProduct

Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment

2021

[EN] Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in Xe-136. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a Th-228 calibration source. We train a network on Monte Carlo-simulat…

Nuclear and High Energy PhysicsPhysics - Instrumentation and DetectorsCalibration (statistics)Computer Science::Neural and Evolutionary ComputationNuclear physicsFOS: Physical sciencesTopology (electrical circuits)01 natural sciencesConvolutional neural networkAtomicPartícules (Física nuclear)High Energy Physics - ExperimentInteraccions electró-positróTECNOLOGIA ELECTRONICAHigh Energy Physics - Experiment (hep-ex)Particle and Plasma PhysicsDouble beta decay0103 physical sciencesDark Matter and Double Beta Decay (experiments)NuclearNuclear Matrixlcsh:Nuclear and particle physics. Atomic energy. Radioactivity010306 general physicsElectron-positron interactionsMathematical PhysicsParticles (Nuclear physics)PhysicsQuantum Physics010308 nuclear & particles physicsbusiness.industryEvent (computing)Network onSIGNAL (programming language)MolecularFísicaPattern recognitionDetectorInstrumentation and Detectors (physics.ins-det)Beta DecayDouble beta decayNuclear & Particles PhysicsDoble desintegració betaIdentification (information)lcsh:QC770-798Física nuclearArtificial intelligencebusinessJournal of High Energy Physics
researchProduct

Artificial neural networks for neutron/ γ discrimination in the neutron detectors of NEDA

2020

Three different Artificial Neural Network architectures have been applied to perform neutron/? discrimination in NEDA based on waveform and time-of-flight information. Using the coincident ?-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms. Narodowe Centrum Nau…

Nuclear and High Energy Physics[formula omitted]-ray spectroscopyNeutron detectorComputer Science::Neural and Evolutionary Computationγ -ray spectroscopy[PHYS.NEXP]Physics [physics]/Nuclear Experiment [nucl-ex]01 natural sciences030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicineCoincident0103 physical sciencesMachine learningNeutron detectionWaveformNeutron[PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det]InstrumentationComputingMilieux_MISCELLANEOUSPhysicsArtificial neural networkArtificial neural networksPulse-shape discriminationn- γ discrimination010308 nuclear & particles physicsbusiness.industryPattern recognitionData setn-[formula omitted] discriminationFeature (computer vision)n-? discriminationAGATAArtificial intelligencey-ray spectroscopybusiness
researchProduct

Classification and retrieval on macroinvertebrate image databases

2011

Aquatic ecosystems are continuously threatened by a growing number of human induced changes. Macroinvertebrate biomonitoring is particularly efficient in pinpointing the cause-effect structure between slow and subtle changes and their detrimental consequences in aquatic ecosystems. The greatest obstacle to implementing efficient biomonitoring is currently the cost-intensive human expert taxonomic identification of samples. While there is evidence that automated recognition techniques can match human taxa identification accuracy at greatly reduced costs, so far the development of automated identification techniques for aquatic organisms has been minimal. In this paper, we focus on advancing …

NymphAquatic OrganismsInsectaDatabases FactualComputer scienceBayesian probabilityta1172Health InformaticsMachine learningcomputer.software_genreData retrievalRiversSupport Vector MachinesImage Processing Computer-AssistedAnimalsMultilayer perceptronsEcosystemta113Network architectureBenthic macroinvertebrateta112Artificial neural networkta213business.industryBayesian networkBayes TheoremPerceptronClassificationRadial basis function networksComputer Science ApplicationsSupport vector machineBiomonitoringBayesian NetworksData miningArtificial intelligenceNeural Networks ComputerbusinesscomputerClassifier (UML)AlgorithmsEnvironmental MonitoringComputers in Biology and Medicine
researchProduct