DocumentCode
2030574
Title
Stability of the generalised lotto-type competitive learning
Author
Luk, Andrew ; Lien, Sandra
Author_Institution
St. B&P Neural Investments Pty Ltd., Westleigh, NSW, Australia
Volume
3
fYear
1999
fDate
1999
Firstpage
1191
Abstract
Introduces a generalised idea of a lotto-type competitive learning (LTCL) algorithm where one or more winners exist. The winners are divided into tiers, with each tier being rewarded differently. Again, the losers are all penalised equally. A set of dynamic LTCL equations is then introduced to assist the study of the stability of the generalised LTCL. It is shown that if a K-orthant exists in the LTCL´s state space, which is an attracting invariant set of the network´s flow, it will converge to a fixed point
Keywords
equations; generalisation (artificial intelligence); stability; state-space methods; unsupervised learning; K-orthant; attracting invariant set; convergence; dynamic equations; fixed point; generalised lotto-type competitive learning algorithm; network flow; penalties; rewards; stability; state space; winner tiers; Counting circuits; Equations; Investments; Neural networks; Neurons; Prototypes; Stability analysis; State-space methods; Virtual colonoscopy;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location
Perth, WA
Print_ISBN
0-7803-5871-6
Type
conf
DOI
10.1109/ICONIP.1999.844706
Filename
844706
Link To Document