Title
Properties Of Learning In Artmap
Keywords
Adaptive resonance theory; ART1; ARTMAP; Learning; Neural network; Pattern recognition
Abstract
In this paper we consider the ARTMAP architecture for situations requiring learning of many-to-one maps. It is shown that if ARTMAP is repeatedly presented with a list of input/output pairs, it establishes the required mapping in at most Ma-1 list presentations, where Ma corresponds to the total number of ones in each one of the input patterns. Other useful properties, associated with the learning of the mapping represented by an arbitrary list of input/output pairs, are also examined. These properties reveal some of the characteristics of learning in ARTMAP when it is used as a tool in establishing an arbitrary mapping from a binary input space to a binary output space. The results presented in this paper are valid for the fast learning case, and for small βa values, where βa is a parameter associated with the adaptation of bottom-up weights in one of the ART1 modules of ARTMAP. © 1994.
Publication Date
1-1-1994
Publication Title
Neural Networks
Volume
7
Issue
3
Number of Pages
495-506
Document Type
Article
Identifier
scopus
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/0893-6080(94)90083-3
Copyright Status
Unknown
Socpus ID
0028312869 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0028312869
STARS Citation
Georgiopoulos, Michael; Huang, Juxin; and Heileman, Gregory L., "Properties Of Learning In Artmap" (1994). Scopus Export 1990s. 390.
https://stars.library.ucf.edu/scopus1990/390