Implementing probabilistic neural networks

Fabio Ancona*, Anna Maria Colla**,
Stefano Rovetta*, and Rodolfo Zunino*


* Department of Biophysical and Electronics Engineering,
  University of Genova - Via all'Opera Pia 11a 16145 Genova, Italy
**Elsag Bailey S.p.A.




Neural Comput & Applic (1998)7:37-51
(c) 1998 Springer-Verlag London Limited




ABSTRACT

A modified PNN training algorithm is proposed. The standard PNN, though
requiring a very short training time, when implemented in hardware exhibits
the drawbacks of being costly in terms of classification time and of requiring
an unlimited number of units. The proposed modification overcomes the
latter drawback by introducing an elimination criterion
to avoid the storage of unnecessary patterns. The distortion in
the density estimation introduced by this criterion is compensated
for by a cross-validation procedure to adapt the network parameters.
The present paper deals with a specific real-world application,
i.e., handwritten character classification. The proposed algorithm makes
it possible to realize the PNN in hardware, and, at the same time,
compensates for some inadequacies arising from the theoretical basis
of the PNN, which does not perform well with small training sets.}


kEYWORDS

Digital neural processor;
Generalization;
Hardware implementation;
Probabilistic Neural Networks;
Random optimization