Title :
Synthesis of a k-winners-take-all neural network using linear programming with bounded variables
Author :
Ferreira, L.V. ; Kaszkurewicz, E. ; Bhaya, A.
Author_Institution :
Dept. of Electr. Eng., Fed. Univ. of Rio de Janeiro, Brazil
Abstract :
A k-winners-take-all (KWTA) problem is formulated as a linear programming (LP) problem with bounded variables. The solution set of the LP problem determines the winners. The LP problem is converted into an unconstrained optimization problem with two exact penalty functions, that is solved by using a gradient descent method implemented as a neural network. Theoretical results ensuring the convergence to the correct solution are provided.
Keywords :
convergence; gradient methods; linear programming; network synthesis; neural nets; optimisation; KWTA; LP; bounded variables; convergence; gradient descent method; k-winners-take-all problem; linear programming; neural network synthesis; penalty functions; unconstrained optimization problem; Circuits; Convergence; Functional programming; Lagrangian functions; Linear programming; Lyapunov method; Network synthesis; Neural networks; Optimization methods; Pattern recognition;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223781
