NONLINEAR SWITCHED-CAPACITOR NEURAL NETWORKS FOR OPTIMIZATION PROBLEMS

被引：199

作者：

RODRIGUEZVAZQUEZ, A ^{[1
]}

DOMINGUEZCASTRO, R ^{[1
]}

RUEDA, A ^{[1
]}

HUERTAS, JL ^{[1
]}

SANCHEZSINENCIO, E ^{[1
]}

机构：

[1] TEXAS A&M UNIV SYST,DEPT ELECT ENGN,COLLEGE STN,TX 77843

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS | 1990年 / 37卷 / 03期

关键词：

D O I：

10.1109/31.52732

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A systematic approach is presented for the design of analog “neural” nonlinear programming solvers using switched-capacitor (SC) integrated circuit techniques. The method is based on formulating a dynamic gradient system whose state evolves in time towards the solution point of the corresponding programming problem. A “neuron” cell for the linear and the quadratic problem suitable for monolithic implementation is introduced. The design of this “neuron” and its corresponding “synapses” using switched-capacitor techniques are considered in detail. A SC circuit architecture based on a reduced set of basic building blocks with high modularity is presented. Simulation results using a mixed-mode simulator (DIANA) [1] and experimental results from breadboard prototypes are included, illustrating the validity of the proposed techniques. © 1990 IEEE

引用

页码：384 / 398

页数：15

共 27 条

[1]

ARNOUT G, 1983, DIANA V7E USERS GUID

[2]

Bernard T., 1988, 1988 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.88CH2458-8), P1217, DOI 10.1109/ISCAS.1988.15146

[3]

CHUA LO, 1984, IEEE T CIRCUITS SYST, V31, P182, DOI 10.1109/TCS.1984.1085482

[4]

DOMINGUEZCASTRO R, 1989, THESIS U SEVILLE

[5]

ELLEITHY N, 1985, 28TH P IEEE MIDW S C, P199

[6]

Gregorian R., 1986, ANALOG MOS INTEGRATE, P505

[7]

HAUSNER A, 1971, ANALOG ANALOG HYBRID

[8]

HOPFIELD JJ, 1985, BIOL CYBERN, V52, P141

[9] ARTIFICIAL NEURAL NETWORKS [J].

HOPFIELD, JJ .

IEEE CIRCUITS AND DEVICES MAGAZINE, 1988, 4 (05) :3-10

[10]

Horio Y., 1988, 1988 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.88CH2458-8), P495, DOI 10.1109/ISCAS.1988.14972

← 1 2 3 →