Title :
Second-order neural nets for constrained optimization
Author :
Zhang, Shengwei ; Zhu, Xianing ; Zou, Li-He
Author_Institution :
Exper Vision Inc., San Jose, CA, USA
fDate :
11/1/1992 12:00:00 AM
Abstract :
Analog neural nets for constrained optimization are proposed as an analogue of Newton´s algorithm in numerical analysis. The neural model is globally stable and can converge to the constrained stationary points. Nonlinear neurons are introduced into the net, making it possible to solve optimization problems where the variables take discrete values, i.e., combinatorial optimization
Keywords :
mathematics computing; neural nets; numerical analysis; optimisation; combinatorial optimization; constrained optimization; constrained stationary points; neural model; nonlinear neurons; numerical analysis; second order neural nets; Constraint optimization; Differential equations; Hopfield neural networks; Lagrangian functions; Neural networks; Neurons; Numerical analysis; Simulated annealing; Subspace constraints; Very large scale integration;
Journal_Title :
Neural Networks, IEEE Transactions on
