Corpus ID: 18882602

D-optimal Bayesian Interrogation for Parameter and Noise Identification of Recurrent Neural Networks

@article{Pczos2008DoptimalBI,
  title={D-optimal Bayesian Interrogation for Parameter and Noise Identification of Recurrent Neural Networks},
  author={Barnab{\'a}s P{\'o}czos and Andr{\'a}s L{\"o}rincz},
  journal={ArXiv},
  year={2008},
  volume={abs/0801.1883}
}
  • Barnabás Póczos, András Lörincz
  • Published 2008
  • Computer Science, Mathematics
  • ArXiv
  • We introduce a novel online Bayesian method for the identification of a family of noisy recurrent neural networks (RNNs). We develop Bayesian active learning technique in order to optimize the interrogating stimuli given past experiences. In particular, we consider the unknown parameters as stochastic variables and use the D-optimality principle, also known as `\emph{infomax method}', to choose optimal stimuli. We apply a greedy technique to maximize the information gain concerning network… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    Towards Independent Subspace Analysis in Controlled Dynamical Systems

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Controlled Complete ARMA Independent Process Analysis

    VIEW 1 EXCERPT
    CITES METHODS

    InfoMax Bayesian Learning of the Furuta Pendulum

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND

    Population Dynamics In A Model Closed Ecosystem

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND