Now showing items 1-20 of 20

  • Adaptively learning probabilistic deterministic automata from data streams 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2014-07)
    Article
    Restricted access - publisher's policy
    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 ...
  • A lower bound for learning distributions generated by probabilistic automata 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2010)
    Conference report
    Open Access
    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. ...
  • A New abstract combinatorial dimension for exact learning via queries 

    Balcázar Navarro, José Luis; Castro Rabal, Jorge; Guijarro Guillem, David (2000-02)
    External research report
    Open Access
    We introduce an abstract model of exact learning via queries that can be instantiated to all the query learning models currently in use, while being closer to them than previous unificatory attempts. We present a ...
  • A note on bounded query learning 

    Castro Rabal, Jorge (2005-04)
    External research report
    Open Access
    We study in this note the relationships between two usual models of learning via queries: the so-called exact and bounded learning models. One of our goals is to point out under which conditions the learning dimension ...
  • A Note on learning decision lists 

    Castro Rabal, Jorge (1995-01)
    External research report
    Open Access
    We show an algorithm that learns decision lists via equivalence queries, provided that a set G including all terms of the target list is given. The algorithm runs in time polynomial in the cardinality of G. From this last ...
  • Bootstrapping and learning PDFA in data streams 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (2012)
    Conference report
    Open Access
    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 ...
  • Learning nearly monotone k-term DNF 

    Castro Rabal, Jorge; Guijarro Guillem, David; Lavín Puente, Víctor Angel (1996-09)
    External research report
    Open Access
    This note studies the learnability of the class k-term DNF with a bounded number of negations per term. We study the case of learning with membership queries alone, and give tight upper and lower bounds on the ...
  • Learning PDFA with asynchronous transitions 

    Balle Pigem, Borja de; Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2010)
    Conference lecture
    Open Access
    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
    Restricted access - publisher's policy
    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 ...
  • Learning probability distributions generated by finite-state machines 

    Castro Rabal, Jorge; Gavaldà Mestre, Ricard (Springer, 2016)
    Part of book or chapter of book
    Open Access
    We review methods for inference of probability distributions generated by probabilistic automata and related models for sequence generation. We focus on methods that can be proved to learn in the inference in the limit ...
  • On the query complexity of quantum learners 

    Castro Rabal, Jorge (2005-06)
    External research report
    Open Access
    This paper introduces a framework for quantum exact learning via queries, the so-called quantum protocol. It is shown that usual protocols in the classical learning setting have quantum counterparts. A combinatorial notion, ...
  • 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)
    Conference report
    Open Access
    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 ...
  • Power to invest 

    Castro Rabal, Jorge; Gabarró Vallès, Joaquim; Serna Iglesias, María José (2018)
    Conference report
    Open Access
    In this post recession time it is important to measure the possibilities offered by a society in relation to investments. To do that, we consider an investment schema I= (R;R_1,...,R_n) where R is a lower bound on the ...
  • Query, PACS and simple-PAC learning 

    Castro Rabal, Jorge; Guijarro Guillem, David (1998-01)
    External research report
    Open Access
    We study a distribution dependent form of PAC learning that uses probability distributions related to Kolmogorov complexity. We relate the PACS model, defined by Denis, D'Halluin and Gilleron, with the standard simple-PAC ...
  • Simple PAC learning of simple decision lists 

    Castro Rabal, Jorge; Balcázar Navarro, José Luis (1995-06)
    External research report
    Open Access
    We prove that log n-decision lists - the class of decision lists such that all their terms have low Kolmogorov complexity - are learnable in the simple PAC learning model. The proof is based on a transformation from an ...
  • The Consistency dimension and distribution-dependent learning from queries 

    Balcázar Navarro, José Luis; Castro Rabal, Jorge; Guijarro Guillem, David (2000-05-01)
    External research report
    Open Access
    We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and ...
  • The Consistency dimension and distribution-dependent learning from queries: (extended abstract with appendices) 

    Balcázar Navarro, José Luis; Castro Rabal, Jorge; Guijarro Guillem, David; Simon, Hans-Ulrich (1999-12)
    External research report
    Open Access
    We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership ...
  • The Plogi and ACi-1 operators on the polynomial time hierarchy 

    Castro Rabal, Jorge; Seara Ojea, Carlos (1993-11)
    External research report
    Open Access
    In a previous paper ([CS-92]) we studied the agreement of operators P_{log^i} and AC^{i-1} acting on NP. In this article we extend this work to other classes of the polynomial time hierarchy. We show that on Sigma_k^p, ...
  • The robustness of periodic orchestrations in uncertain evolving environments 

    Castro Rabal, Jorge; Gabarró Vallès, Joaquim; Serna Iglesias, María José; Stewart, Alan (Springer, 2015)
    Conference report
    Open Access
    A framework for assessing the robustness of long-duration repetitive orchestrations in uncertain evolving environments is proposed. The model assumes that service-based evaluation environments are stable over short ...
  • Web apps and imprecise probabilities 

    Castro Rabal, Jorge; Gabarró Vallès, Joaquim; Serna Iglesias, María José (Springer, 2018)
    Conference report
    Open Access
    We propose a model for the behaviour of Web apps in the unreliable WWW. Web apps are described by orchestrations. An orchestration mimics the personal use of the Web by defining the way in which Web services are invoked. ...