P.  JenoPaul, M.  SreeDevi, 
    Parameter Based Kalman Filter Training in Neural Network,
    International Journal of Soft Computing,
    Volume 8,Issue 5,
    2013,
    Pages 352-355,
    ISSN 1816-9503,
    ijscomp.2013.352.355,
    (https://makhillpublications.co/view-article.php?doi=ijscomp.2013.352.355)
    Abstract: Neural Networks (NNs) have been employed in many applications 
  in recent years. A neural network is an interconnection of a number of artificial 
  neurons that simulate a biological brain system. It has the ability to approximate 
  nonlinear functions and can achieve higher degree of fault tolerance. NNs have 
  been successfully introduced into power electronics circuits where a NN replaced 
  a large and memory demanding look-up table to generate the switching angles. 
  The neural network controllers for engine idle speed and Air/Fuel (A/F) ratio 
  control produce signals that affect the operation of the engine while the neural 
  network models are used to describe various aspects of engine operation as a 
  function of measurable engine outputs. This study aims to study the behavior 
  of the parameter based kalman filtering in neural network.
    Keywords: KF-kalman filtering;neural networks;NNs;brain;fault