Search results for "Upervised learning"

showing 10 items of 87 documents

Using deep neural networks for kinematic analysis: Challenges and opportunities

2020

Kinematic analysis is often performed in a lab using optical cameras combined with reflective markers.\ud With the advent of artificial intelligence techniques such as deep neural networks, it is now possible\ud to perform such analyses without markers, making outdoor applications feasible. In this paper I summarise\ud 2D markerless approaches for estimating joint angles, highlighting their strengths and limitations.\ud In computer science, so-called ‘‘pose estimation” algorithms have existed for many years. These methods\ud involve training a neural network to detect features (e.g. anatomical landmarks) using a process called\ud supervised learning, which requires ‘‘training” images to be …

Motion analysisComputer scienceProcess (engineering)media_common.quotation_subject0206 medical engineeringBiomedical EngineeringBiophysicsneuroverkot02 engineering and technologyMachine learningcomputer.software_genreTask (project management)QA7603 medical and health sciences0302 clinical medicineDeep LearningArtificial IntelligenceHumansOrthopedics and Sports MedicineQuality (business)liikeanalyysiPosemedia_commonQMliikeoppiArtificial neural networkGV557_SportsT1business.industrymotion analysisRehabilitationSupervised learningdeep neural networkartificial intelligence020601 biomedical engineeringBiomechanical Phenomenakoneoppiminenkinematicsmarkerless trackingArtificial intelligenceNeural Networks ComputerbusinessTransfer of learningcomputer030217 neurology & neurosurgeryAlgorithms
researchProduct

Semi-Supervised Classification Method for Hyperspectral Remote Sensing Images

2004

A new approach to the classification of hyperspectral images is proposed. The main problem with supervised methods is that the learning process heavily depends on the quality of the training data set. In remote sensing, the training set is useful only for simultaneous images or for images with the same classes taken under the same conditions; and, even worse, the training set is frequently not available. On the other hand, unsupervised methods are not sensitive to the number of labelled samples since they work on the whole image. Nevertheless, relationship between clusters and classes is not ensured. In this context, we propose a combined strategy of supervised and unsupervised learning met…

Learning vector quantizationTraining setArtificial neural networkComputer sciencebusiness.industryHyperspectral imagingPattern recognitionMultispectral pattern recognitionRobustness (computer science)Unsupervised learningArtificial intelligencebusinessHyMapRemote sensing
researchProduct

Remote Photoplethysmography Based on Implicit Living Skin Tissue Segmentation

2016

International audience; Region of interest selection is an essential part for remote photoplethysmography (rPPG) algorithms. Most of the time, face detection provided by a supervised learning of physical appearance features coupled with skin detection is used for region of interest selection. However, both methods have several limitations and we propose to implicitly select living skin tissue via their particular pulsatility feature. The input video stream is decomposed into several temporal superpixels from which pulse signals are extracted. Pulsatility measure for each temporal superpixel is then used to merge pulse traces and estimate the photoplethysmogram signal. This allows to select …

[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingComputer science[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing0206 medical engineering[INFO.INFO-IM] Computer Science [cs]/Medical Imaging02 engineering and technology[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]01 natural sciences010309 optics[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingSkin tissueRegion of interestPhotoplethysmogram0103 physical sciences[INFO.INFO-IM]Computer Science [cs]/Medical ImagingSegmentationComputer visionFace detection[ SDV.IB.IMA ] Life Sciences [q-bio]/Bioengineering/Imaging[ INFO.INFO-IM ] Computer Science [cs]/Medical Imagingbusiness.industrySupervised learning[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020601 biomedical engineering[SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/ImagingArtificial intelligencebusiness
researchProduct

Discovering single classes in remote sensing images with active learning

2012

When dealing with supervised target detection, the acquisition of labeled samples is one of the most critical phases: the samples must be yet representative of the class of interest, but must also be found among a vast majority of non-target examples. Moreover, the efficiency of the search is also an issue, since the samples labeled as background are not used by target detectors such as the support vector data description (SVDD). In this work we propose a competitive and effective approach to identify the most relevant training samples for one-class classification based on the use of an active learning strategy. The SVDD classifier is first trained with insufficient target examples. It is t…

Active learningComputer scienceActive learning (machine learning)business.industryPattern recognitionSemi-supervised learningRemote sensingMachine learningcomputer.software_genreSupport vector machineActive learningLife ScienceSupport Vector Data DescriptionArtificial intelligencebusinessClassifier (UML)computerChange detection2012 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

A Tsetlin Machine with Multigranular Clauses

2019

The recently introduced Tsetlin Machine (TM) has provided competitive pattern recognition accuracy in several benchmarks, however, requires a 3-dimensional hyperparameter search. In this paper, we introduce the Multigranular Tsetlin Machine (MTM). The MTM eliminates the specificity hyperparameter, used by the TM to control the granularity of the conjunctive clauses that it produces for recognizing patterns. Instead of using a fixed global specificity, we encode varying specificity as part of the clauses, rendering the clauses multigranular. This makes it easier to configure the TM because the dimensionality of the hyperparameter search space is reduced to only two dimensions. Indeed, it tur…

HyperparameterLearning automataComputer sciencebusiness.industrySupervised learningPattern recognitionGranularityArtificial intelligenceENCODEPropositional calculusbusinessRendering (computer graphics)Curse of dimensionality
researchProduct

Archetypoids: A new approach to define representative archetypal data

2015

[EN] The new concept archetypoids is introduced. Archetypoid analysis represents each observation in a dataset as a mixture of actual observations in the dataset, which are pure type or archetypoids. Unlike archetype analysis, archetypoids are real observations, not a mixture of observations. This is relevant when existing archetypal observations are needed, rather than fictitious ones. An algorithm is proposed to find them and some of their theoretical properties are introduced. It is also shown how they can be obtained when only dissimilarities between observations are known (features are unavailable). Archetypoid analysis is illustrated in two design problems and several examples, compar…

Statistics and ProbabilityConvex hullArchetypebusiness.industryApplied MathematicsNon-negative matrix factorizationExtremal pointType (model theory)Unsupervised learningNon-negative matrix factorizationComputational MathematicsComputational Theory and MathematicsConvex hullUnsupervised learningExtremal pointArtificial intelligencebusinessArchetypeMathematics
researchProduct

Simulated Annealing Technique for Fast Learning of SOM Networks

2011

The Self-Organizing Map (SOM) is a popular unsupervised neural network able to provide effective clustering and data visualization for multidimensional input datasets. In this paper, we present an application of the simulated annealing procedure to the SOM learning algorithm with the aim to obtain a fast learning and better performances in terms of quantization error. The proposed learning algorithm is called Fast Learning Self-Organized Map, and it does not affect the easiness of the basic learning algorithm of the standard SOM. The proposed learning algorithm also improves the quality of resulting maps by providing better clustering quality and topology preservation of input multi-dimensi…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniComputer Science::Machine LearningArtificial IntelligenceSOM Simulated annealing Clustering Fast learningArtificial neural networkWake-sleep algorithmbusiness.industryComputer scienceTopology (electrical circuits)computer.software_genreAdaptive simulated annealingGeneralization errorData visualizationComputingMethodologies_PATTERNRECOGNITIONArtificial IntelligenceSimulated annealingUnsupervised learningData miningbusinessCluster analysisSelf Organizing map simulated annealingcomputerSoftware
researchProduct

On the impact of forgetting on learning machines

1995

People tend not to have perfect memories when it comes to learning, or to anything else for that matter. Most formal studies of learning, however, assume a perfect memory. Some approaches have restricted the number of items that could be retained. We introduce a complexity theoretic accounting of memory utilization by learning machines. In our new model, memory is measured in bits as a function of the size of the input. There is a hierarchy of learnability based on increasing memory allotment. The lower bound results are proved using an unusual combination of pumping and mutual recursion theorem arguments. For technical reasons, it was necessary to consider two types of memory : long and sh…

Theoretical computer scienceActive learning (machine learning)Computer scienceSemi-supervised learningMutual recursionArtificial IntelligenceInstance-based learningHierarchyForgettingKolmogorov complexitybusiness.industryLearnabilityAlgorithmic learning theoryOnline machine learningInductive reasoningPumping lemma for regular languagesTerm (time)Computational learning theoryHardware and ArchitectureControl and Systems EngineeringArtificial intelligenceSequence learningbusinessSoftwareCognitive psychologyInformation SystemsJournal of the ACM
researchProduct

An on-line learning method for face association in personal photo collection

2012

Due to the widespread use of cameras, it is very common to collect thousands of personal photos. A proper organization is needed to make the collection usable and to enable an easy photo retrieval. In this paper, we present a method to organize personal photo collections based on ''who'' is in the picture. Our method consists in detecting the faces in the photo sequence and arranging them in groups corresponding to the probable identities. This problem can be conveniently modeled as a multi-target visual tracking where a set of on-line trained classifiers is used to represent the identity models. In contrast to other works where clustering methods are used, our method relies on a probabilis…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniInformation retrievalComputer sciencebusiness.industrySemi-supervised learningUSableDigital libraryMachine learningcomputer.software_genreSet (abstract data type)Face descriptor Data association On-line learning Semi-supervised learning Digital librariesFace (geometry)Signal ProcessingIdentity (object-oriented programming)Eye trackingComputer Vision and Pattern RecognitionArtificial intelligencebusinessCluster analysiscomputer
researchProduct

Supervised learning of time-independent Hamiltonians for gate design

2018

We present a general framework to tackle the problem of finding time-independent dynamics generating target unitary evolutions. We show that this problem is equivalently stated as a set of conditions over the spectrum of the time-independent gate generator, thus transforming the task to an inverse eigenvalue problem. We illustrate our methodology by identifying suitable time-independent generators implementing Toffoli and Fredkin gates without the need for ancillae or effective evolutions. We show how the same conditions can be used to solve the problem numerically, via supervised learning techniques. In turn, this allows us to solve problems that are not amenable, in general, to direct ana…

Theoretical computer scienceDiagonalFOS: Physical sciencesGeneral Physics and AstronomyInverseToffoli gate02 engineering and technologysupervised learning01 natural sciencesUnitary statequantum computingSettore FIS/03 - Fisica Della Materia010305 fluids & plasmasSet (abstract data type)Computer Science::Hardware Architecturesymbols.namesakeComputer Science::Emerging Technologiesquant-ph020204 information systems0103 physical sciences0202 electrical engineering electronic engineering information engineering010306 general physicsEigenvalues and eigenvectorsQuantum computerMathematicsPhysicsFlexibility (engineering)Discrete mathematicsQuantum PhysicsSupervised learningInverse problemHermitian matrixmachine learningQubitsymbolsPairwise comparisonquantum circuitsQuantum Physics (quant-ph)Hamiltonian (quantum mechanics)Generator (mathematics)Quantum Information and Measurement (QIM) V: Quantum Technologies
researchProduct