Equilibrium States of LYAM System
Source abstract
Abstract
In this paper, a study of the Lyapunov Associative Memory (LYAM) is given. This system is constructed by a set of ordinary differential equations, and its stable equilibrium states store pattern cluster information. The study shows that the single-class system is always globally stable; the many-class system has many unstable activation states and at least one stable category state representing the learned information. A rigorous stability study of the many-class system is difficult, and it remains to be investigated.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Applications · Neural Networks Stability and Synchronization · Nonlinear Dynamics and Pattern Formation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering Southern Illinois University at Carbondale Carbondale, IL 62901-6603
References (10)
Show source-provided references
1. Aizerman, M.A. · Automation and Remote Control · 1964 · 25 · 821
2. Aizerman, M.A. · Automanon and Remote Control · 1964 · 25 · 1175
3. 10.1103/PhysRevA.32.100710.1103/PhysRevA.32.1007 ↗
4. 10.1016/S0893-6080(05)80008-510.1016/S0893-6080(05)80008-5 ↗
5. 10.1103/PhysRevA.37.213410.1103/PhysRevA.37.2134 ↗
6. 10.1109/IJCNN.1989.11855910.1109/IJCNN.1989.118559 ↗
7. 10.1109/21.4403910.1109/21.44039 ↗
8. 10.1073/pnas.79.8.255410.1073/pnas.79.8.2554 ↗
9. 10.1117/12.94274810.1117/12.942748 ↗
10. Sayeh, M.R., A. Ragu and H.H. Szu. 1991. "Design of Unsupervised Classifier", IJCNN, Seattle, WA, pp. 11417-11422.