Analysis and synthesis of a class of neural networks; Linear systems operating on a closed hypercube
- Dept. of Electrical and Computer Engineering, Univ. of Notre Dame, Notre Dame, IN (US)
The authors investigate the qualitative properties of a class of neural networks described by a system of first-order linear ordinary differential equations which are defined on a closed hypercube of the state space with solutions extended to the boundary of the hypercube. When solutions are located on the boundary of the hypercube, the system is the to be in saturated mode. The class of systems considered herein retain the basic structure of the Hopfield model and is easier to analyze, synthesize and implement than the Hopfield model. An efficient analysis method is developed which can be used to completely determine the set of asymptotically stable equilibrium points and the set of unstable equilibrium points. The latter set can be used to estimate the domains of attraction for the elements of the former set. The synthesis procedure which the authors previously developed is modified and applied to the present class of neural networks. The class of systems considered herein can easily be implemented in analog integrated circuits. The applicability of the present results is demonstrated by means of several examples.
- OSTI ID:
- 7183918
- Journal Information:
- IEEE Transactions on Circuits and Systems (Institute of Electrical and Electronics Engineers); (USA), Vol. 36:11; ISSN 0098-4094
- Country of Publication:
- United States
- Language:
- English
Similar Records
Analysis and synthesis of a class of neural networks; Variable structure systems with infinite gain
A hypercube compact neural network
Related Subjects
HYPERCUBE COMPUTERS
COMPUTER ARCHITECTURE
INTEGRATED CIRCUITS
LINEAR PROGRAMMING
NEURAL NETWORKS
COMPUTERIZED SIMULATION
ALGORITHMS
ASYMPTOTIC SOLUTIONS
DESIGN
DIFFERENTIAL EQUATIONS
PARALLEL PROCESSING
COMPUTERS
ELECTRONIC CIRCUITS
EQUATIONS
MATHEMATICAL LOGIC
MICROELECTRONIC CIRCUITS
PROGRAMMING
SIMULATION
990200* - Mathematics & Computers