Главная

Pouyan Rafiei Fard

  1. Variational Iteration Method for Image Restoration.

    Чт, 09/02/2010 - 15:01 — SomNambul
    Authors: Keyvan Yahya, Pouyan Rafiei Fard, Jafar Biazar, Hossein Azari
    Subjects: Numerical Analysis
    Abstract

    The famous Perona-Malik (P-M) equation which was at first introduced for
    image restoration has been solved via various numerical methods. In this paper
    we will solve it for the first time via applying a new numerical method called
    the Variational Iteration Method (VIM) and the correspondent approximated
    solutions will be obtained for the P-M equation with regards to relevant error
    analysis. Through implementation of our algorithm we will access some effective
    results which are deserved to be considered as worthy as the other solutions
    issued by the other methods.

  2. A Reinforcement Learning Model Using Neural Networks for Music Sight Reading Learning Problem.

    Втр, 07/06/2010 - 15:03 — SomNambul
    Authors: Keyvan Yahya, Pouyan Rafiei Fard
    Subjects: Learning
    Abstract

    Music Sight Reading is a complex process that when it is occurred in the
    brain, some learning attributes would be emerged. Besides giving a model based
    on actor-critic method in the Reinforcement Learning, the agent is considered
    to have a neural network structure. We studied on where the sight reading
    process is happened and also a serious problem which is how the synaptic
    weights would be adjusted through the learning process. The model we offer here
    is a computational model on which an updated weights equation to fixing the
    weights is accompanied too.

  3. Computational Model of Music Sight Reading: A Reinforcement Learning Approach.

    Втр, 07/06/2010 - 15:02 — SomNambul
    Authors: Keyvan Yahya, Pouyan Rafiei Fard
    Subjects: Artificial Intelligence
    Abstract

    Although the Music Sight Reading process usually has been studied from the
    cognitive or neurological view points, but the computational learning methods
    like the Reinforcement Learning have not yet been used to modeling of such
    processes. In this paper with regards to essential properties of our specific
    problem, we consider the value function concept and will indicate that the
    optimum policy can be obtained by the method we offer without to be getting
    involved with computing of the complex value functions which are in most of
    cases inexact.

Math-arch

RSS-материал