A wawelet based heuristic to dimension Neural Networks for simple signal approximation

  • Authors:

  • Gabriele Colombini;Davide Sottara;Luca Luccarini;Paola Mello

  • Affiliations:

  • DEIS, Faculty of Engineering, University of Bologna Viale Risorgimento 2, 40100 Bologna (BO) Italy;DEIS, Faculty of Engineering, University of Bologna Viale Risorgimento 2, 40100 Bologna (BO) Italy;ENEA --ACS PROT IDR --Water Resource Management Section, Via Martiri di Monte Sole 4, 40129 Bologna (BO) Italy;DEIS, Faculty of Engineering, University of Bologna Viale Risorgimento 2, 40100 Bologna (BO) Italy

  • Venue:
  • Proceedings of the 2009 conference on Neural Nets WIRN09: Proceedings of the 19th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, May 28--30 2009
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Before training a feed forward neural network, one needs to define its architecture. Even in simple feed-forward networks, the number of neurons of the hidden layer is a fundamental parameter, but it is not generally possible to compute its optimal value a priori. It is good practice to start from an initial number of neurons, then build, train and test several different networks with a similar hidden layer size, but this can be excessively expensive when the data to be learned are simple, while some real-time constraints have to be satisfied. This paper shows a heuristic method for dimensioning and initializing a network under such assumptions. The method has been tested on a project for waste water treatment monitoring.