Improving ARTMAP learning through variable vigilance.
Int J Neural Syst
; 11(6): 509-22, 2001 Dec.
Article
in En
| MEDLINE
| ID: mdl-11852436
ABSTRACT
This paper presents a mechanism to vary the vigilance parameter in the RePART fuzzy neural network. This mechanism helps to smooth out the problem of category proliferation which affects ARTMAP-based networks. Empirical experiments show that the use of variable vigilance improves the performance of the RePART model while, at the same time, requiring a less complex structure.
Search on Google
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Attention
/
Neural Networks, Computer
/
Fuzzy Logic
/
Learning
/
Models, Neurological
Type of study:
Prognostic_studies
Language:
En
Journal:
Int J Neural Syst
Journal subject:
ENGENHARIA BIOMEDICA
/
INFORMATICA MEDICA
Year:
2001
Document type:
Article
Affiliation country:
United kingdom
Publication country:
SG
/
SINGAPORE
/
SINGAPUR
/
SINGAPURA