Identifying Stochastic Processes with Mixture Density Networks

  title={Identifying Stochastic Processes with Mixture Density Networks},
  author={Christian Schittenkopf and Georg Dor and Engelbert J. Dockner},
In this paper we investigate the use of mixture density networks (MDNs) for identifying complex stochastic processes. Regular mul-tilayer perceptrons (MLPs), widely used in time series processing, assume a gaussian conditional noise distribution with constant variance, which is unrealistic in many applications, such as nancial time series (which are known… CONTINUE READING