Search results for "NEURAL NETWORK"

showing 10 items of 1385 documents

Hierarchies of Self-Organizing Maps for action recognition

2016

We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction and clustering of the feature space. It represents the dynamics of the stream of posture frames in action sequences as activity trajectories over time. The second layer in the hierarchy consists of another SOM which clusters the activity trajectories of the first-layer SOM and learns to represent action prototypes. The third - and last - layer of the hierarchy consists of a neural network that learns to label action prototypes of the second-laye…

Self-organizing mapComputer scienceIntention understandingCognitive NeuroscienceFeature vectorExperimental and Cognitive PsychologySelf-Organizing Map02 engineering and technologyAction recognition03 medical and health sciences0302 clinical medicineArtificial Intelligence0202 electrical engineering electronic engineering information engineeringLayer (object-oriented design)Cluster analysisSet (psychology)Artificial neural networkbusiness.industryDimensionality reductionNeural networkAction (philosophy)020201 artificial intelligence & image processingArtificial intelligencebusinessHierarchical model030217 neurology & neurosurgerySoftwareCognitive Systems Research
researchProduct

Analysis of motor control and behavior in multi agent systems by means of artificial neural networks

2004

Abstract This article gives a short introduction to Self-Organizing Maps, a particular form of Artificial Neural Networks and shows by some examples, how these approaches can be used in order to analyze and visualize time series data originating from complex systems. The methods shown in this article have originally been developed for the analysis of RoboCup robot soccer games, a special kind of so-called Multi Agent Systems. Although this application has no direct connection to biomechanics, the examples shown here may give an impression of the abilities of Neural Networks in the field of Time Series Analysis in general. Because of the abstractness of the methods, it appears to be very lik…

Self-organizing mapEngineeringMovementModels NeurologicalBiophysicsComplex systemContext (language use)Motor ActivityMachine learningcomputer.software_genreField (computer science)AnimalsHumansComputer SimulationOrthopedics and Sports MedicineDiagnosis Computer-AssistedArtificial neural networkbusiness.industryTime delay neural networkMulti-agent systemRoboticsRobotNeural Networks ComputerArtificial intelligencebusinesscomputerAlgorithmsClinical Biomechanics
researchProduct

Self-organizing maps: A new digital architecture

1991

An original hardware architecture implementing the self-organizing feature maps, which is one of the most powerful and efficent neural network algorithm, is presented. The architecture, contrary to the most investigated hardware implementations of neural networks, is a full digital one and it may be easily built by using the standard VLSI techniques.

Self-organizing mapHardware architectureVery-large-scale integrationArtificial neural networkComputer architectureFeature (computer vision)Computer scienceApplications architectureArchitectureDigital architecture
researchProduct

The Hydrothermal System of Solfatara Crater (Campi Flegrei, Italy) Inferred From Machine Learning Algorithms

2019

Two machine learning algorithms were applied to three multivariate datasets acquired at Solfatara volcano. Our aim was to find an unbiased and coherent synthesis among the large amount of data acquired within the crater and along two orthogonal vertical NNE- and WNW-trending cross-sections. The first algorithm includes a new approach for a soft K-means clustering based on the use of the silhouette index to control the color palette of the clusters. The second algorithm which uses the self-organizing maps incorporates an alternative method for choosing the number of nodes of the neural network which aims to avoid the need for downstream clustering of the results of the classification. Both m…

Self-organizing mapMultivariate statistics010504 meteorology & atmospheric sciencesself-organizing maps010502 geochemistry & geophysicsMachine learningcomputer.software_genre01 natural sciencesSilhouetteImpact craterSolfataralcsh:ScienceCluster analysisK-means0105 earth and related environmental sciencesExploration geophysicsArtificial neural networkbusiness.industryk-means clusteringseismic methodsmachine learningGeneral Earth and Planetary Scienceslcsh:QArtificial intelligenceCampi FlegreibusinesscomputerAlgorithmGeologyFrontiers in Earth Science
researchProduct

Forecasting daily urban electric load profiles using artificial neural networks

2004

The paper illustrates a combined approach based on unsupervised and supervised neural networks for the electric energy demand forecasting of a suburban area with a prediction time of 24 h. A preventive classification of the historical load data is performed during the unsupervised stage by means of a Kohonen's self organizing map (SOM). The actual forecast is obtained using a two layered feed forward neural network, trained with the back propagation with momentum learning algorithm. In order to investigate the influence of climate variability on the electricity consumption, the neural network is trained using weather data (temperature, relative humidity, global solar radiation) along with h…

Self-organizing mapSettore ING-IND/11 - Fisica Tecnica AmbientaleElectrical loadArtificial neural networkRenewable Energy Sustainability and the Environmentbusiness.industryComputer scienceEnergy Engineering and Power Technologyelectricity consumption neural networksDemand forecastingGridcomputer.software_genreBackpropagationFuel TechnologyNuclear Energy and EngineeringFeedforward neural networkElectricityData miningTelecommunicationsbusinesscomputerEnergy Conversion and Management
researchProduct

A neural network approach to movement pattern analysis.

2004

Movements are time-dependent processes and so can be modelled by time-series of coordinates: E.g., each articulation has geometric coordinates; the set of the coordinates of the relevant articulations build a high-dimensional configuration. These configurations--or "patterns"--give reason for analysing movements by means of neural networks: The Kohonen Feature Map (KFM) is a special type of neural network, which (after having been coined by training with appropriate pattern samples) is able to recognize single patterns as members of pattern clusters. This way, for example, the particular configurations of a given movement can be identified as belonging to respective configuration clusters, …

Self-organizing mapSimilarity (geometry)Computer scienceProcess (engineering)MovementBiophysicsExperimental and Cognitive PsychologyWalkingRunningSet (abstract data type)Software DesignOrientationFeature (machine learning)Computer GraphicsHumansOrthopedics and Sports MedicineMuscle SkeletalGaitStochastic ProcessesArtificial neural networkbusiness.industryBody movementPattern recognitionGeneral MedicineBiomechanical PhenomenaJoggingData Interpretation StatisticalTrajectoryArtificial intelligenceNeural Networks ComputerbusinessAlgorithmsHuman movement science
researchProduct

Visual Data Mining With Self-organizing Maps for “Self-monitoring” Data Analysis

2016

Data collected in psychological studies are mainly characterized by containing a large number of variables (multidimensional data sets). Analyzing multidimensional data can be a difficult task, especially if only classical approaches are used (hypothesis tests, analyses of variance, linear models, etc.). Regarding multidimensional models, visual techniques play an important role because they can show the relationships among variables in a data set. Parallel coordinates and Chernoff faces are good examples of this. This article presents self-organizing maps (SOM), a multivariate visual data mining technique used to provide global visualizations of all the data. This technique is presented as…

Self-organizing mapSociology and Political ScienceComputer scienceself-organizing mapscomputer.software_genreTask (project management)tutorial03 medical and health sciences0302 clinical medicinevisual data mining030212 general & internal medicinePersonalitat sociopatològicaArtificial neural networkCognitive restructuringMultidimensional dataData sciencePsicologiaSelf-monitoringEarly adolescentsdata scienceData miningartificial neural networkscomputer030217 neurology & neurosurgerySocial Sciences (miscellaneous)Sociological Methods & Research
researchProduct

Tree Structured Self-Organizing Maps

1999

Publisher Summary This chapter provides an overview of the tree structured self-organizing maps (TS-SOM). It was originally intended as a fast implementation of the self-organizing map (SOM). The chapter explains that TS-SOM is a constructive smoother for a class of dimension reduction problems. There is a well known relation between self-organizing maps and principal curves. Unfortunately in most presentations it is derived by simple reasoning, avoiding the mathematical statement of the problem, which is essential to understand how efficient SOM implementations can be constructed. In this chapter, SOM is derived as a numerical solution of a generic model in a continuous domain, which diffe…

Self-organizing mapTree (data structure)Theoretical computer scienceArtificial neural networkRelation (database)Simple (abstract algebra)Computer scienceDimensionality reductionConstructiveDomain (software engineering)
researchProduct

A Study of the Simulated Evolution of the Spectral Sensitivity of Visual Agent Receptors

2001

In this article we study a model for the evolution of the spectral sensitivity of visual receptors for agents in a continuous virtual environment. The model uses a genetic algorithm (GA) to evolve the agent sensors along with the control of the agents by requiring the agents to solve certain tasks in the simulation environment. The properties of the evolved sensors are analyzed for different scenarios. In particular, it is shown that the GA is able to find a balance between sensor costs and agent performance in such a way that the spectral sensor sensitivity reflects the emission spectrum of the target objects and that the capability of the sensors to evolve can help the agents significantl…

Sensory Receptor CellsComputer scienceReal-time computingRoboticsEnvironmentcomputer.software_genreGeneral Biochemistry Genetics and Molecular BiologyTask (computing)Spectral sensitivityArtificial IntelligenceVirtual machineBraitenberg vehicleGenetic algorithmAnimalsComputer SimulationNeural Networks ComputerSensitivity (control systems)computerAlgorithmsPhotic StimulationSimulationArtificial Life
researchProduct

Sabiedrības attieksmes modelēšana, izmantojot sentimenta analīzi

2017

Šī darba mērķis ir izveidot sentimenta analīzes risinājumu, kuru paredzēts izmantot informācijas ieguves sistēmas koncepta izstrādē. Sentimenta analīze tiks veikta sociālo tīklu ziņām. Darba izstrādes sākumā tika veikta esošo sentimenta analīzes risinājumu izpēte un to rezultātu salīdzināšana. Tālāk tika veikta publiski pieejamo treniņdatu korpusu ievākšana. Papildus iegūtajiem datiem, tika izveidots latviešu valodai paredzēts sentimenta analīzes treniņdatu korpuss. Korpusa izveidošanas procesā tika veikta informācijas ieguves sistēmas koncepta izveide. Pēc nepieciešamo treniņdatu savākšanas, tika veikta ilgās īstermiņa atmiņas rekurentā neirona tīkla izveidošana un optimizēšana. Darba rezu…

Sentiment analysisSentimenta analīzeArtificial neural networksDatorzinātneMākslīgie neironu tīkli
researchProduct