Relaxation of the stability condition of the complex-valued neural networks

IEEE Transactions on Neural Networks

Volumn 12, Issue 5, 2001, Pages 1260-1262

  Lee, D L ^a  

^a TA HWA INSTITUTE OF TECHNOLOGY   (Taiwan)

Author keywords

Asynchronous update mode; Complex valued neural networks; Energy function

Indexed keywords

ASSOCIATIVE STORAGE; COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; DIGITAL IMAGE STORAGE; ITERATIVE METHODS; MATRIX ALGEBRA; PROBABILITY; RANDOM PROCESSES; VECTORS;

ASYNCHRONOUS UPDATE MODE; COMPLEX VALUED NEURAL NETWORK; ENERGY FUNCTION; GRAY SCALE IMAGES; HERMITIAN ASSUMPTION;

NEURAL NETWORKS;

EID: 0035440681     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.950156     Document Type: Letter

References (10)

1. Complex-valued multistate neural associative memory
2. Neural networks and physical systems with emergent computational abilities
3. Neurons with graded response have collective computational properties like those of two-state neurons
4. Generalized Hopfield networks with multiple stable states
5. Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule
6. New stability conditions for Hopfield networks in partial simultaneous update mode
7. Global convergence and asymptotic stability of asymmetric Hopfield networks
8. Asymmetric Hopfield networks: Theory and applications
9. Location and stability of the high-gain equilibria of nonlinear neural networks
10. Memory and learning of sequential patterns by nonmonotone neural networks