LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge

 

LARCA és un grup de recerca de nivell internacional en temes d'aprenentatge i mineria de dades, anàlisi de dades i lingüística matemàtica. Típicament, abordem els problemes des de principis matemàtics sòlids, usant eines de modelització i tècniques de l'algorísmia, complexitat computacional, teoria d'autòmats, lògica, matemàtica discreta, estadística, i sistemes dinàmics. Estem iniciant
col·laboracions amb empreses i altres institucions per tal d'aplicar les nostres solucions al problemes del món real.

http://futur.upc.edu/LARCA

LARCA es un grupo de investigación de nivel internacional en temas de aprendizaje y minería de datos, análisis de datos y lingüística matemática. Típicamente, abordamos los problemas desde principios matemáticos sólidos, usando técnicas de modelización de la algoritmia, la complejidad computacional, teoría de autómatas, lógica, matemática discreta, estadística y sistemas dinámicos. Estamos iniciando colaboraciones con empresas e instituciones para la aplicación de nuestras soluciones a contextos reales.

http://futur.upc.edu/LARCA

LARCA is an international research group working on data mining, machine learning, data analysis, and mathematical linguistics. We typically approach problems from sound mathematical principles, using modelling tools and techniques from algorithmics, computational complexity, automata theory, logic, discrete mathematics, statistics, and dynamic systems. We are also starting partnerships with companies and other institutions to apply our solutions to real-world problems.

http://futur.upc.edu/LARCA

LARCA is an international research group working on data mining, machine learning, data analysis, and mathematical linguistics. We typically approach problems from sound mathematical principles, using modelling tools and techniques from algorithmics, computational complexity, automata theory, logic, discrete mathematics, statistics, and dynamic systems. We are also starting partnerships with companies and other institutions to apply our solutions to real-world problems.

http://futur.upc.edu/LARCA

Enviaments recents

  • Neighborhood-based stopping criterion for contrastive divergence 

    Romero Merino, Enrique; Mazzanti Castrillejo, Fernando Pablo; Delgado Pin, Jordi (2018-07)
    Article
    Accés obert
    Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence (CD) learning algorithm, an ...

  • New ensemble methods for evolving data streams 

    Bifet Figuerol, Albert Carles; Holmes, Geoffrey; Pfahringer, Bernhard; Kirkby, R; Gavaldà Mestre, Ricard (Association for Computing Machinery (ACM), 2009)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Advanced analysis of data streams is quickly becoming a key area of data mining research as the number of applications demanding such processing increases. Online mining when such data streams evolve over time, that is ...

  • Characterizing covers of functional dependencies using FCA 

    Codocedo, Victor; Baixeries i Juvillà, Jaume; Kaytoue, Mehdi; Napoli, Amedeo (2018)
    Text en actes de congrés
    Accés obert
    Functional dependencies (FDs) can be used for various important operations on data, for instance, checking the consistency and the quality of a database (including databases that contain complex data). Consequently, a ...

  • The origins of Zipf's meaning-frequency law 

    Ferrer Cancho, Ramon; Vitevitch, Michael S. (2018-11)
    Article
    Accés obert
    In his pioneering research, G.K. Zipf observed that more frequent words tend to have more meanings, and showed that the number of meanings of a word grows as the square root of its frequency. He derived this relationship ...

  • A new spectral method for latent variable models 

    Ruffini, Matteo; Casanellas Rius, Marta; Gavaldà Mestre, Ricard (2018-05-22)
    Article
    Accés restringit per política de l'editorial
    We present an algorithm for the unsupervised learning of latent variable models based on the method of moments. We give efficient estimates of the moments for two models that are well known, e.g., in text mining, the ...

  • Ordocoordinación: cómo organizar 700 estudiantes en un nuevo campus (y no morir en el intento) 

    Castro Rabal, Jorge; Farreres de la Morena, Xavier; Gabarró Vallès, Joaquim; Nivela Alós, M. Pilar Brígida; Pérez Poch, Antoni; Pino Blanco, Elvira; Rivero Almeida, José Miguel (Asociación de Enseñantes Universitarios de la Informática (AENUI), 2018)
    Text en actes de congrés
    Accés obert
    Since Autumn Term 2017 the Department of Computer Science of the Universitat Politecnica de Catalunya UPC-BarcelonaTech is in charge of teaching ”Fundamentals of Programming” in the new DiagonalBeso ´s Campus, at EEBE ...

  • Embedding in law of discrete time ARMA processes in continuous time stationary processes 

    Arratia Quesada, Argimiro Alejandro; Cabaña, Ana Alejandra; Cabaña Perez, Enrique (2018-12-01)
    Article
    Accés restringit per política de l'editorial
    Given any stationary time series {Xn : n ¿ Z} satisfying an ARMA(p, q) model for arbitrary p and q with infinitely divisible innovations, we construct a continuous time stationary process {xt : t ¿ R} such that the ...

  • Emergence of linguistic laws in human voice 

    González Torre, Iván; Luque Serrano, Bartolo; Lacasa, Lucas; Miramontes, Octavio; Hernández Fernández, Antonio (2017)
    Comunicació de congrés
    Accés obert
    Linguistic laws constitute one of the quantitative cornerstones of modern cognitive sciences and have been routinely investigated in written corpora, or in the equivalent transcription of oral corpora. This means that ...

  • Norm estimates for the hardy operator in terms of B-p weights 

    Boza Rocho, Santiago; Soria de Diego, Javier (2017-06-01)
    Article
    Accés obert
    We study the explicit dependence of the Bp-constant of the weight, [w]Bp , in the estimates of the norm of the Hardy operator acting on non-increasing functions in L p (w) or L p,8(w).

  • Logspace self-reducibility 

    Balcázar Navarro, José Luis (Institute of Electrical and Electronics Engineers (IEEE), 1988)
    Text en actes de congrés
    Accés obert
    A definition of self-reducibility is proposed to deal with logarithmic space complexity classes. A general property derived from the definition is used to prove known results comparing uniform and nonuniform complexity ...

  • Weak-type boundedness of the Fourier transform on rearrangement invariant function spacest 

    Boza Rocho, Santiago; Soria de Diego, Javier (2018-06-08)
    Article
    Accés obert
    We study several questions about the weak-type boundedness of the Fourier transform F on rearrangement invariant spaces. In particular, we characterize the action of F as a bounded operator from the minimal Lorentz space ...

  • Optimization models of natural communication 

    Ferrer Cancho, Ramon (2018-07-03)
    Article
    Accés restringit per política de l'editorial
    A family of information theoretic models of communication was introduced more than a decade ago to explain the origins of Zipf’s law for word frequencies. The family is a based on a combination of two information theoretic ...

Mostra'n més