DocumentCode :
3142960
Title :
Prototyping neural networks learn Lyme borreliosis
Author :
Rovetta, Stefano ; Zunino, Rodolfo ; Buffrini, Laura ; Rovetta, Guido
Author_Institution :
Fac. of Eng., Genova Univ., Italy
fYear :
1995
fDate :
9-10 Jun 1995
Firstpage :
111
Lastpage :
117
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 backpropagation. The aim of the work is to compare the three methods in view of their use as analysis tools, to explore 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 prototypal 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
Keywords :
backpropagation; knowledge representation; medical computing; self-organising feature maps; Lyme borreliosis; analysis tools; circular backpropagation; feedforward neural models; knowledge representation; medical application; neural gas networks; neural networks; self organizing maps; Back; Classification algorithms; Databases; Design engineering; Diseases; Knowledge representation; Medical diagnostic imaging; Neural networks; Prototypes; Self organizing feature maps;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer-Based Medical Systems, 1995., Proceedings of the Eighth IEEE Symposium on
Conference_Location :
Lubbock, TX
Print_ISBN :
0-8186-7117-3
Type :
conf
DOI :
10.1109/CBMS.1995.465431
Filename :
465431
Link To Document :
بازگشت