Analog neural nonderivative optimizers
Contribuinte(s) |
Universidade Estadual Paulista (UNESP) |
---|---|
Data(s) |
20/05/2014
20/05/2014
01/07/1998
|
Resumo |
Continuous-time neural networks for solving convex nonlinear unconstrained;programming problems without using gradient information of the objective function are proposed and analyzed. Thus, the proposed networks are nonderivative optimizers. First, networks for optimizing objective functions of one variable are discussed. Then, an existing one-dimensional optimizer is analyzed, and a new line search optimizer is proposed. It is shown that the proposed optimizer network is robust in the sense that it has disturbance rejection property. The network can be implemented easily in hardware using standard circuit elements. The one-dimensional net is used as a building block in multidimensional networks for optimizing objective functions of several variables. The multidimensional nets implement a continuous version of the coordinate descent method. |
Formato |
629-638 |
Identificador |
http://dx.doi.org/10.1109/72.701176 IEEE Transactions on Neural Networks. New York: IEEE-Inst Electrical Electronics Engineers Inc., v. 9, n. 4, p. 629-638, 1998. 1045-9227 http://hdl.handle.net/11449/9651 10.1109/72.701176 WOS:000074419800005 |
Idioma(s) |
eng |
Publicador |
Institute of Electrical and Electronics Engineers (IEEE) |
Relação |
IEEE Transactions on Neural Networks |
Direitos |
closedAccess |
Palavras-Chave | #analog networks #coordinate descent #derivative free optimization #unconstrained optimization |
Tipo |
info:eu-repo/semantics/article |