Error-Entropy Minimization for Dynamical Systems Modeling

  title={Error-Entropy Minimization for Dynamical Systems Modeling},
  author={Jernej Zupanc},
Recent publications have presented many successful usages of elements from information theory in adaptive systems training. Error-entropy has been proven to outperform mean squared error as a cost function in many artificially generated data sets, but still few applications to real world data have been published. In this paper, we design a neural network trained with error-entropy minimization criterion and use it for dynamical systems modeling on artificial as well as real world data… CONTINUE READING

Similar Papers

Loading similar papers…