شماره ركورد كنفرانس :
4057
عنوان مقاله :
Neural Network as a Tool for Solving Nonsmooth Optimization Problems
عنوان به زبان ديگر :
Neural Network as a Tool for Solving Nonsmooth Optimization Problems
پديدآورندگان :
Hosseini Alireza hosseini.alireza@ut.ac.ir School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran
كليدواژه :
neurodynamic optimization , convergence , recurrent neural network , analog circuit
عنوان كنفرانس :
چهارمين كنفرانس بين المللي آناليز غير خطي و بهينه سازي
چكيده فارسي :
A neural network model for solving a class of nonsmooth optimization problems is proposed. The state trajectory of
the corresponding recurrent neural network will converges globally to optimal set of the problem. In the structure of the proposed
model there is not any penalty parameter.
چكيده لاتين :
A neural network model for solving a class of nonsmooth optimization problems is proposed. The state trajectory of
the corresponding recurrent neural network will converges globally to optimal set of the problem. In the structure of the proposed
model there is not any penalty parameter.
