Search results for "embedding"

showing 10 items of 175 documents

Model selection based product kernel learning for regression on graphs

2013

The choice of a suitable graph kernel is intrinsically hard and often cannot be made in an informed manner for a given dataset. Methods for multiple kernel learning offer a possible remedy, as they combine and weight kernels on the basis of a labeled training set of molecules to define a new kernel. Whereas most methods for multiple kernel learning focus on learning convex linear combinations of kernels, we propose to combine kernels in products, which theoretically enables higher expressiveness. In experiments on ten publicly available chemical QSAR datasets we show that product kernel learning is on no dataset significantly worse than any of the competing kernel methods and on average the…

Graph kernelTraining setMultiple kernel learningComputer sciencebusiness.industryPattern recognitionSemi-supervised learningMachine learningcomputer.software_genreKernel (linear algebra)Kernel methodKernel embedding of distributionsPolynomial kernelKernel (statistics)Radial basis function kernelArtificial intelligenceTree kernelbusinesscomputerProceedings of the 28th Annual ACM Symposium on Applied Computing
researchProduct

A structural cluster kernel for learning on graphs

2012

In recent years, graph kernels have received considerable interest within the machine learning and data mining community. Here, we introduce a novel approach enabling kernel methods to utilize additional information hidden in the structural neighborhood of the graphs under consideration. Our novel structural cluster kernel (SCK) incorporates similarities induced by a structural clustering algorithm to improve state-of-the-art graph kernels. The approach taken is based on the idea that graph similarity can not only be described by the similarity between the graphs themselves, but also by the similarity they possess with respect to their structural neighborhood. We applied our novel kernel in…

Graph kernelbusiness.industryPattern recognitionComputingMethodologies_PATTERNRECOGNITIONKernel methodString kernelPolynomial kernelKernel embedding of distributionsRadial basis function kernelArtificial intelligenceTree kernelCluster analysisbusinessMathematicsProceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
researchProduct

Detection of Hate Speech Spreaders using Convolutional Neural Networks

2021

In this paper we describe a deep learning model based on a Convolutional Neural Network (CNN). The model was developed for the Profiling Hate Speech Spreaders (HSSs) task proposed by PAN 2021 organizers and hosted at the 2021 CLEF Conference. Our approach to the task of classifying an author as HSS or not (nHSS) takes advantage of a CNN based on a single convolutional layer. In this binary classification task, on the tests performed using a 5-fold cross validation, the proposed model reaches a maximum accuracy of 0.80 on the multilingual (i.e., English and Spanish) training set, and a minimum loss value of 0.51 on the same set. As announced by the task organizers, the trained model presente…

Hate Speech Deep Learning Author Profiling Convolutional Neural Network Word EmbeddingDeep LearningEnglishWord EmbeddingTwitterHate SpeechAuthor ProfilingConvolutional Neural NetworkSpanish
researchProduct

Weighted Sobolev spaces and exterior problems for the Helmholtz equation

1987

Weighted Sobolev spaces are used to settle questions of existence and uniqueness of solutions to exterior problems for the Helmholtz equation. Furthermore, it is shown that this approach can cater for inhomogeneous terms in the problem that are only required to vanish asymptotically at infinity. In contrast to the Rellich–Sommerfeld radiation condition which, in a Hilbert space setting, requires that all radiating solutions of the Helmholtz equation should satisfy a condition of the form ( ∂ / ∂ r − i k ) u ∈ L 2 ( Ω ) , r = | x | ∈ Ω ⊂ R n , it is shown here that radiating solutions satisfy a condition of the form ( 1 + r ) − 1 2 ( ln ( e + r ) ) − 1 2 δ u ∈ L 2 ( Ω ) , 0 < δ < 1 2 …

Helmholtz equationmedia_common.quotation_subjectMathematical analysisHilbert spacePoincaré inequalityInfinitySobolev spacesymbols.namesakeGeneral EnergysymbolsEmbeddingUniquenessmedia_commonMathematicsProceedings of the Royal Society of London. A. Mathematical and Physical Sciences
researchProduct

Intersecting Defects and Supergroup Gauge Theory

2021

Journal of physics / A 54(43), 435401 (2021). doi:10.1088/1751-8121/ac2716

High Energy Physics - TheoryInstantondimension: 5supersymmetry: algebra[PHYS.MPHY]Physics [physics]/Mathematical Physics [math-ph]General Physics and Astronomy01 natural sciencesHigh Energy Physics::Theorytopological [string]Mathematics - Quantum AlgebraGauge theorytopological stringsMathematical PhysicsdefectsPhysics[PHYS]Physics [physics][PHYS.HTHE]Physics [physics]/High Energy Physics - Theory [hep-th]Chern-Simons termsupergroups[PHYS.MPHY] Physics [physics]/Mathematical Physics [math-ph]algebra [supersymmetry]5 [dimension]geometrical [transition]Modeling and SimulationEmbeddingBPSinstanton010307 mathematical physicsSupergroupStatistics and Probabilitysupersymmetry [gauge field theory]defectFOS: Physical sciencesDuality (optimization)Unitary state530Supersymmetric gauge theoryTheoretical physicsIntersectiongauge field theory: supersymmetry0103 physical sciencesFOS: Mathematicsstring: topologicalQuantum Algebra (math.QA)ddc:530Abelian grouptransition: geometrical010308 nuclear & particles physicsStatistical and Nonlinear PhysicsHigh Energy Physics - Theory (hep-th)Chern-Simons theory[PHYS.HTHE] Physics [physics]/High Energy Physics - Theory [hep-th]
researchProduct

The Segre embedding of the quantum conformal superspace

2018

In this paper study the quantum deformation of the superflag Fl(2|0, 2|1,4|1), and its big cell, describing the complex conformal and Minkowski superspaces respectively. In particular, we realize their projective embedding via a generalization to the super world of the Segre map and we use it to construct a quantum deformation of the super line bundle realizing this embedding. This strategy allows us to obtain a description of the quantum coordinate superring of the superflag that is then naturally equipped with a coaction of the quantum complex conformal supergroup SL_q(4|1).

High Energy Physics - TheoryPhysicsPure mathematicsQuantum geometryGeneral MathematicsFOS: Physical sciencesGeneral Physics and AstronomyConformal mapMathematical Physics (math-ph)Mathematics - Rings and AlgebrasSuperspaceSegre embeddingHigh Energy Physics - Theory (hep-th)Line bundleRings and Algebras (math.RA)Mathematics - Quantum AlgebraMinkowski spacequantum geometryFOS: MathematicsQuantum Algebra (math.QA)EmbeddingQuantumMathematical Physics
researchProduct

External derivations of internal groupoids

2008

If His a G-crossed module, the set of derivations of Gin H is a monoid under the Whitehead product of derivations. We interpret the Whitehead product using the correspondence between crossed modules and internal groupoids in the category of groups. Working in the general context of internal groupoids in a finitely complete category, we relate derivations to holomorphisms, translations, affine transformations, and to the embedding category of a groupoid. (C) 2007 Elsevier B.V. All rights reserved.

Higher-dimensional algebraAlgebra and Number TheoryComplete categoryCategory of groupsContext (language use)derivations crossed modules internal groupoids holomorphismsAlgebraSettore MAT/02 - AlgebraMathematics::K-Theory and HomologyMathematics::Category TheoryMonoid (category theory)EmbeddingAffine transformationMathematics::Symplectic GeometryMathematicsWhitehead productJournal of Pure and Applied Algebra
researchProduct

Supravital Uptake of Methylene Blue by Dendritic Cells within Stratified Squamous Epithelia: a Light and Electron Microscope Study

1996

Electron microscopic data on methylene blue staining of dendritic cells in the epithelia of the soft palate and skin of the mouse after supravital dye injection are presented. The ultra-structural details were compared with corresponding light microscopic findings. Methylene blue stained tissue was fixed by immersion in a paraformaldehyde-glutaraldehyde solution containing phosphomolybdic acid. The ensuing dye precipitate was stabilized by ammonium heptamolybdate. The light microscopic investigation revealed that selective staining of dendritic cells depended on the presence of ambient oxygen. In addition, delicate morphological characteristics, like spinous structures of the dendrites, wer…

HistologyConnective tissueEpitheliumlaw.inventionMicechemistry.chemical_compoundlawOrganellemedicineAnimalsColoring AgentsSkinParaffin EmbeddingStaining and LabelingEpithelial CellsDendritic CellsGeneral MedicineEpitheliumStainingMethylene BlueMicroscopy ElectronMedical Laboratory Technologymedicine.anatomical_structureVital stainchemistryBiochemistryCytoplasmBiophysicsPalate SoftElectron microscopeMethylene blueBiotechnic & Histochemistry
researchProduct

Deep Metric Learning for Transparent Classification of Covid-19 X-Ray Images

2022

This work proposes an interpretable classifier for automatic Covid-19 classification using chest X-ray images. It is based on a deep learning model, in particular, a triplet network, devoted to finding an effective image embedding. Such embedding is a non-linear projection of the images into a space of reduced dimension, where homogeneity and separation of the classes measured by a predefined metric are improved. A K-Nearest Neighbor classifier is the interpretable model used for the final classification. Results on public datasets show that the proposed methodology can reach comparable results with state of the art in terms of accuracy, with the advantage of providing interpretability to t…

Image diagnosisSettore INF/01 - InformaticaChest-X-rayCovid-19Embeddings
researchProduct

Continuous spectrum for a two phase eigenvalue problem with an indefinite and unbounded potential

2020

Abstract We consider a two phase eigenvalue problem driven by the ( p , q ) -Laplacian plus an indefinite and unbounded potential, and Robin boundary condition. Using a modification of the Nehari manifold method, we show that there exists a nontrivial open interval I ⊆ R such that every λ ∈ I is an eigenvalue with positive eigenfunctions. When we impose additional regularity conditions on the potential function and the boundary coefficient, we show that we have smooth eigenfunctions.

Indefinite unbounded potentialPure mathematicsNehari manifoldApplied Mathematics010102 general mathematicsContinuous spectrumBoundary (topology)Function (mathematics)Robin boundary conditionMathematics::Spectral TheoryEigenfunction01 natural sciences(pq)-LaplacianRobin boundary condition010101 applied mathematicsSettore MAT/05 - Analisi MatematicaLagrange multiplier rule0101 mathematicsSobolev embedding theoremNehari manifoldLaplace operatorAnalysisEigenvalues and eigenvectorsMathematicsJournal of Differential Equations
researchProduct