TY - JOUR
T1 - A Dynamical Adaptive Resonance Architecture
AU - Heileman, Gregory L.
AU - Georgiopoulos, Michael
AU - Abdallah, Chaouki
N1 - Funding Information:
Manuscript received September 24, 1993; revised March 5, 1993. This work was supported in part by the Boeing Computer Services under Contract W-300445, and the Florida High Technology and Industry Council.
PY - 1994/11
Y1 - 1994/11
N2 - A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg [1], It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART 1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.
AB - A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg [1], It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART 1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.
UR - http://www.scopus.com/inward/record.url?scp=0028546055&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0028546055&partnerID=8YFLogxK
U2 - 10.1109/72.329684
DO - 10.1109/72.329684
M3 - Article
AN - SCOPUS:0028546055
SN - 1045-9227
VL - 5
SP - 873
EP - 889
JO - IEEE Transactions on Neural Networks
JF - IEEE Transactions on Neural Networks
IS - 6
ER -