A complete proof of global exponential convergence of a neural network for quadratic optimization with bound constraints

IEEE Transactions on Neural Networks

Volumn 12, Issue 3, 2001, Pages 636-639

  Liang, X B ^a  

^a UNIVERSITY OF DELAWARE   (United States)

Author keywords

Global exponential stability; Quadratic optimization with bound constraints; Recurrent neural networks

Indexed keywords

BOUNDARY CONDITIONS; COMPUTER SIMULATION; CONFORMAL MAPPING; CONSTRAINT THEORY; CONVERGENCE OF NUMERICAL METHODS; DIFFERENTIAL EQUATIONS; LYAPUNOV METHODS; MATHEMATICAL MODELS; MATRIX ALGEBRA; QUADRATIC PROGRAMMING; THEOREM PROVING; VECTORS;

CONTRACTIVE NETWORKS; GLOBAL EXPONENTIAL STABILITY; QUADRATIC MINIMIZATION PROBLEM; QUADRATIC OPTIMIZATION;

RECURRENT NEURAL NETWORKS;

EID: 0035330651     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.925567     Document Type: Letter

References (9)

1. Exponential stability and a systematic synthesis of a neural network for quadratic minimization
2. Error in proof of exponential convergence
3. Neural network for quadratic optimization with bound constraints
4. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit
5. Neural networks for nonlinear programming
6. On the solution of large quadratic programming problems with bound constraints
7. Stability in contractive nonlinear neural networks
8. Exponential stability of a neural network for bound-constrained quadratic optimization