Now showing items 1-2 of 2

  • Discovering ship navigation patterns towards environmental impact modeling 

    Gutiérrez, Alberto; Buchaca, David; Berral García, Josep Lluís (Barcelona Supercomputing Center, 2017-05-04)
    Conference report
    Open Access
    In this work a data pipe-line to manage and extract patterns from time-series is described. The patterns found with a combination of Conditional Restricted Boltzmann Machine (CRBM) and k-Means algorithms are then validated ...
  • Stopping criteria in contrastive divergence: Alternatives to the reconstruction error 

    Buchaca, David; Romero Merino, Enrique; Mazzanti Castrillejo, Fernando Pablo; Delgado Pin, Jordi (2014)
    Conference report
    Open Access
    Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an ...