Search results for "NEURAL NETWORK"

showing 10 items of 1385 documents

An investigation of the neural circuits underlying reaching and reach-to-grasp movements: from planning to execution

2014

Experimental evidence suggests the existence of a sophisticated brain circuit specifically dedicated to reach-to-grasp planning and execution, both in human and non-human primates (Castiello, 2005). Studies accomplished by means of neuroimaging techniques suggest the hypothesis of a dichotomy between a "reach-to-grasp" circuit, involving the anterior intraparietal area, the dorsal and ventral premotor cortices (PMd and PMv - Castiello and Begliomini, 2008; Filimon, 2010) and a "reaching" circuit involving the medial intraparietal area and the superior parieto-occipital cortex (Culham et al., 2006). However, the time course characterizing the involvement of these regions during the planning …

Stimulus (physiology)lcsh:RC321-571Behavioral NeuroscienceNeuroimagingmotor planningBiological neural networkmedicineReach to graspfunctional magnetic resonance imaging; motor execution; motor planning; reach-to-grasp; reachingOriginal Research Articlelcsh:Neurosciences. Biological psychiatry. NeuropsychiatryBiological PsychiatryBrain networkmedicine.diagnostic_testSettore M-PSI/02 - Psicobiologia E Psicologia FisiologicaGRASPfunctional magnetic resonance imaging (fMRI)reach-to-graspfunctional magnetic resonance imagingreachingmotor executionNeuropsychology and Physiological PsychologyNeurologyPsychiatry and Mental HealthTime courseFunctional magnetic resonance imagingPsychologyNeuroscienceNeuroscience
researchProduct

Experimental and numerical study of noise effects in a FitzHugh-Nagumo system driven by a biharmonic signal

2013

Using a nonlinear circuit ruled by the FitzHugh-Nagumo equations, we experimentally investigate the combined effect of noise and a biharmonic driving of respective high and low frequency F and f. Without noise, we show that the response of the circuit to the low frequency can be maximized for a critical amplitude B of the high frequency via the effect of Vibrational Resonance (V.R.). We report that under certain conditions on the biharmonic stimulus, white noise can induce V.R. The effects of colored noise on V.R. are also discussed by considering an Ornstein-Uhlenbeck process. All experimental results are confirmed by numerical analysis of the system response.

Stochastic Resonancenoisevibrational Resonance[PHYS.PHYS.PHYS-BIO-PH] Physics [physics]/Physics [physics]/Biological Physics [physics.bio-ph]neural network[NLIN.NLIN-PS] Nonlinear Sciences [physics]/Pattern Formation and Solitons [nlin.PS]nonlinear circuits[SPI.TRON] Engineering Sciences [physics]/Electronics
researchProduct

Adaptive sparse representation of continuous input for tsetlin machines based on stochastic searching on the line

2021

This paper introduces a novel approach to representing continuous inputs in Tsetlin Machines (TMs). Instead of using one Tsetlin Automaton (TA) for every unique threshold found when Booleanizing continuous input, we employ two Stochastic Searching on the Line (SSL) automata to learn discriminative lower and upper bounds. The two resulting Boolean features are adapted to the rest of the clause by equipping each clause with its own team of SSLs, which update the bounds during the learning process. Two standard TAs finally decide whether to include the resulting features as part of the clause. In this way, only four automata altogether represent one continuous feature (instead of potentially h…

Stochastic Searching on the Line automatonBoosting (machine learning)decision support systemTK7800-8360Computer Networks and CommunicationsComputer scienceDiscriminative modelFeature (machine learning)Electrical and Electronic EngineeringArtificial neural networkrule-based learninginterpretable machine learninginterpretable AISparse approximationAutomatonRandom forestSupport vector machineVDP::Teknologi: 500Tsetlin MachineXAIHardware and ArchitectureControl and Systems EngineeringSignal ProcessingElectronicsTsetlin automataAlgorithm
researchProduct

Robust linear quadratic mean-field games in crowd-seeking social networks.

2013

We consider a social network where opinions evolve following a stochastic averaging process under the influence of adversarial disturbances. We provide a robust mean-field game model in the spirit of H∞-optimal control, establish existence of a mean-field equilibrium, and analyze its stochastic stability.

Stochastic controlContinuous-time stochastic processMathematical optimizationSocial networkStochastic processbusiness.industryControl (management)mean field gamesRobust controlStochastic neural networkbusinessGame theoryMathematical economicsMathematics
researchProduct

Systematic comparison of Artificial Neural Networks for a SHM procedure applied to Composite Structure

2014

The problems related to damage detection represents a primary concern, particularly in the framework of composite structure. In fact, for this kind of structures barely visible damage can occur. Moreover, one of the major in-service damage of composite aircraft strcutures is represented by disbonds between the stiffeners and the skin undergoing dynamic or post-buckling loads. The effective implementation of a SHM system relies on the synthesis of non-destructive technique (NDT), fracture mechanics, sensors technology, data manipulation and signal processing, and it can receive a great improvement through the use of an Artificial Neural Networks. Different architectures of Artificial Neural …

Structural Health MonitoringComposite damageSettore ING-IND/04 - Costruzioni E Strutture AerospazialiNeural network
researchProduct

A convolutional neural network for virtual screening of molecular fingerprints

2019

In the last few years, Deep Learning (DL) gained more and more impact on drug design because it allows a huge increase of the prediction accuracy in many stages of such a complex process. In this paper a Virtual Screening (VS) procedure based on Convolutional Neural Networks (CNN) is presented, that is aimed at classifying a set of candidate compounds as regards their biological activity on a particular target protein. The model has been trained on a dataset of active/inactive compounds with respect to the Cyclin-Dependent Kinase 1 (CDK1) a very important protein family, which is heavily involved in regulating the cell cycle. One qualifying point of the proposed approach is the use of molec…

Structure (mathematical logic)0303 health sciencesVirtual screening010304 chemical physicsPoint (typography)Computer sciencebusiness.industryDeep learningProcess (computing)Pattern recognition01 natural sciencesConvolutional neural networkDrug designSet (abstract data type)03 medical and health sciencesDeep LearningVirtual Screening0103 physical sciencesMolecular fingerprintsEmbeddingArtificial intelligencebusinessBioactivity prediction030304 developmental biology
researchProduct

Are Neural Networks Imitations of Mind?

2015

Artificial neural networks are often understood as a good way to imitate mind through the web structure of neurons in brain, but the very high complexity of human brain prevents to consider neural networks as good models for human mind;anyway neural networks are good devices for computation in parallel. The difference between feed-forward and feedback neural networks is introduced; the Hopfield network and the multi-layers Perceptron are discussed. In a very weak isomorphism (not similitude) between brain and neural networks, an artificial form of short term memory and of acknowledgement, in Elman neural networks, is proposed.

Structure (mathematical logic)Artificial neural networkQuantitative Biology::Neurons and CognitionArtificial neural networkComputer sciencebusiness.industryComputationComputer Science::Neural and Evolutionary ComputationAcknowledgementShort-term memoryRecurrent networkBrainFeed-forward networkSettore M-FIL/02 - Logica E Filosofia Della ScienzaPerceptroncomputer.software_genreMindSimilitudeHopfield networkArtificial intelligenceData miningbusinesscomputer
researchProduct

Interactive Effects of Explicit Emergent Structure: A Major Challenge for Cognitive Computational Modeling

2015

International audience; David Marr's (1982) three-level analysis of computational cognition argues for three distinct levels of cognitive information processingnamely, the computational, representational, and implementational levels. But Marr's levels areand were meant to bedescriptive, rather than interactive and dynamic. For this reason, we suggest that, had Marr been writing today, he might well have gone even farther in his analysis, including the emergence of structurein particular, explicit structure at the conceptual levelfrom lower levels, and the effect of explicit emergent structures on the level (or levels) that gave rise to them. The message is that today's cognitive scientists …

Structure (mathematical logic)Cognitive scienceFeed backLinguistics and LanguageInteractive emergenceComputer scienceActive symbolsConcept FormationCognitive NeuroscienceComputational cognitionExperimental and Cognitive PsychologyCognitionEmergenceConnectionist modelsHuman-Computer InteractionCognitionAnalogy-makingInteractive effectsArtificial Intelligence[ SDV.NEU ] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]HumansLearning[SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]Neural Networks Computer
researchProduct

The Insect Mushroom Bodies: a Paradigm of Neural Reuse

2013

This paper is devoted to discuss the implementation of models,which are inspired by the fly Drosophila melanogaster and able to handle open problems in the field of robotics such as attention, expectation and sequence learning. The role of the Mushroom Bodies (MBs) in solving these tasks is analyzed in detail and a unifying plausible biologically inspired model is proposed. The developed neural structure is able to show different capabilities in line with the paradigm of neural reuse. The same neural circuit can be exploited to accomplish multiple tasks showing interesting capabilities such as attention, expectation and delayed match-to-sample. The simulation results here reported suggest a…

Structure (mathematical logic)Computer sciencebusiness.industryRoboticsinsect brainReuseMachine learningcomputer.software_genreField (computer science)Neural networks; insect brainBiological significanceMushroom bodiesArtificial intelligenceSequence learningbusinesscomputerNeural networks
researchProduct

Contributions Regarding the Utilization of Neural Networks in SME's Management

2014

Due to the fact that there isnt a clear definition of the terms neural network" and "neuronal network" [1,2], the current paper aims to establish it by a range of comparative research. With the help of some charts, based on the structure of some SMEs (Small and Medium Enterprises), the parts that define the structure of the neuron will be compared with the general structure of an organization, in order to reproduce the neuron in the structuring level of an organization and give a meaning to the term of "organizational neuron. Sometimes it is necessary to take managerial decisions under uncertainty and / or risk, so any method that gives forecasting information to the manager is welcome [3,4…

Structure (mathematical logic)EngineeringKnowledge managementArtificial neural networkbusiness.industryGeneral MedicineStructuringComparative researchArtificial neuronBiological neural networkSmall and medium-sized enterprisesArtificial intelligenceMeaning (existential)businessApplied Mechanics and Materials
researchProduct