Exploració per autor "Balle Pigem, Borja de"

Ara es mostren els items 5-13 de 13

    • Bootstrapping and learning PDFA in data streams 

      Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2012)
      Text en actes de congrés
      Accés obert
      Markovian models with hidden state are widely-used formalisms for modeling sequential phenomena. Learnability of these models has been well studied when the sample is given in batch mode, and algorithms with PAC-like ...

    • Extensions de l'algorisme clàssic de Whitehead 

      Balle Pigem, Borja de (Universitat Politècnica de Catalunya, 2009-02)
      Projecte Final de Màster Oficial
      Accés obert
      L'algoritme clàssic de Whitehead decideix si dues paraules del grup lliure pertanyen o no a la mateixa òrbita per l'acció del grup d'automorfismes. La demostració clàssica és molt combinatòrica i tècnica (i desagradable ...

    • Learning finite-state machines: statistical and algorithmic aspects 

      Balle Pigem, Borja de (Universitat Politècnica de Catalunya, 2013-07-12)
      Tesi
      Accés obert
      The present thesis addresses several machine learning problems on generative and predictive models on sequential data. All the models considered have in common that they can be de ned in terms of nite-state machines. On ...

    • Learning PDFA with asynchronous transitions 

      Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2010)
      Comunicació de congrés
      Accés obert
      In this paper we extend the PAC learning algorithm due to Clark and Thollard for learning distributions generated by PDFA to automata whose transitions may take varying time lengths, governed by exponential distributions.

    • Learning probabilistic automata : a study in state distinguishability 

      Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2013-02-18)
      Article
      Accés restringit per política de l'editorial
      Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability μ of the target machine, besides the number of states and the usual accuracy and confidence parameters. We ...

    • Spectral learning in non-deterministic dependency parsing 

      Luque, Franco M.; Quattoni, Ariadna Julieta; Balle Pigem, Borja de; Carreras Pérez, Xavier (2012)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      In this paper we study spectral learning methods for non-deterministic split head-automata grammars, a powerful hidden-state formalism for dependency parsing. We present a learning algorithm that, like other spectral ...

    • Spectral learning of general weighted automata via constrained matrix completion 

      Balle Pigem, Borja de; Mohri, Mehryar (2012)
      Comunicació de congrés
      Accés obert
      Many tasks in text and speech processing and computational biology require estimating functions mapping strings to real numbers. A broad class of such functions can be defined by weighted automata. Spectral methods based ...

    • Spectral learning of weighted automata: a forward-backward perspective 

      Balle Pigem, Borja de; Carreras Pérez, Xavier; Luque, Franco M.; Quattoni, Ariadna Julieta (2013-10-07)
      Article
      Accés restringit per política de l'editorial
      In recent years we have seen the development of efficient provably correct algorithms for learning Weighted Finite Automata (WFA). Most of these algorithms avoid the known hardness results by defining parameters beyond the ...

    • Spectral regularization for max-margin sequence tagging 

      Quattoni, Ariadna Julieta; Balle Pigem, Borja de; Carreras Pérez, Xavier; Globerson, Amir (2014)
      Text en actes de congrés
      Accés obert
      We frame max-margin learning of latent variable structured prediction models as a convex optimization problem, making use of scoring functions computed by input-output observable operator models. This learning problem can ...