Research Area

  • Title:
    Machine Learning for Signal Processing

  • Keywords:

    linear system identification, nonlinear system identification, regression

  • Description:

    The research aims at widening the range of applicability of artificial neural networks towards the stochastic world, by investigating their ability in approximating input-output random functions and transformations. It will help develop a statistical representation of synthetic and biological signals, by exploiting the properties of different universal approximators of stochastic processes, and apply this result to the problems of signal recognition and synthesis, and will investigate and develop techniques suitable for the supervised or unsupervised statistical identification of non-stationary non-linear systems.

  • Laboratory:

    Embedded Systems and Artificial Intelligence Lab

  • Contact Person:

    Giorgio Biagetti