Now showing items 1-5 of 5

    • Extended linear models with Gaussian prior on the parameters and adaptive expansion vectors 

      Barrio Moliner, Ignacio; Romero Merino, Enrique; Belanche Muñoz, Luis Antonio (Springer, 2007)
      Conference report
      Open Access
      We present an approximate Bayesian method for regression and classification with models linear in the parameters. Similar to the Relevance Vector Machine (RVM), each parameter is associated with an expansion vector. Unlike ...
    • Feature selection methods for the selection of hidden neurons 

      Barrio Moliner, Ignacio (2005-11)
      External research report
      Open Access
      Feature selection techniques try to select the most suitable subset from a set of attributes, some of which can be useless or contain too much noise. Since analyzing all possible subsets has exponential cost, a search is ...
    • On the selection of hidden neurons with heuristic search strategies for approximation 

      Barrio Moliner, Ignacio; Romero Merino, Enrique; Belanche Muñoz, Luis Antonio (2006)
      Conference report
      Open Access
      Feature Selection techniques usually follow some search strategy to select a suitable subset from a set of features. Most neural network growing algorithms perform a search with Forward Selection with the objective of ...
    • Search strategies guided by the evidence for the selection of basis functions in regression 

      Barrio Moliner, Ignacio; Romero Merino, Enrique; Belanche Muñoz, Luis Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2007)
      Conference report
      Open Access
      This work addresses the problem of selecting a subset of basis functions for a model linear in the parameters for regression tasks. Basis functions from a set of candidates are explicitly selected with search methods coming ...
    • Selection of basis functions guided by the L2 soft margin 

      Barrio Moliner, Ignacio; Romero Merino, Enrique; Belanche Muñoz, Luis Antonio (Springer, 2007)
      Conference report
      Open Access
      Support Vector Machines (SVMs) for classification tasks produce sparse models by maximizing the margin. Two limitations of this technique are considered in this work: firstly, the number of support vectors can be large ...