Prototyping Neural Networks Learn Lyme Borreliosis

Stefano Rovetta *, Rodolfo Zunino *, Laura Buffrini **, Guido Rovetta **
University of Genova, Italy
*  Faculty of Engineering, DIBE
** Faculty of Medicine, DIMI


ABSTRACT

In this paper, the application of neural network algorithms
to the study of Lyme borreliosis is addressed. Three
different methods are studied: Self Organizing Maps, Neural
Gas Networks and a new approach currently under development,
called Circular Back Propagation. The aim of the work is to
compare the three methods in view of their use as analysis
tools, to ex-plore the inherent structure of the input data.
The same procedure has been previously applied to
feedforward neural models; the present work focuses on a
particular form of knowledge representation, based on  a
set of proto-typal examples rather than if-then rules. The
Lyme data has been chosen as a case study and represents a
common ground to allow the comparison of the different methods.


SUBJECT TERMS

medical computing; self-organising feature maps; backpropagation;
knowledge representation; neural networks; Lyme borreliosis;
self organizing maps; neural gas networks; circular backpropagation;
analysis tools; feedforward neural models; knowledge representation;
medical application

-----
Proceedings of the 8th IEEE Symposium on Computer-Based Medical Systems
Lubbock, Texas, USA, June 1995, pp. 111-117.

Copyright (c) 1995 Institute of Electrical and Electronics Engineers, Inc.
All rights reserved.