A state-constrained model for cellular nonlinear network optimization

Eric Y. Chou*, Bing J. Sheu, Richard H. Tsai

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

2 Scopus citations

Abstract

A Gm C-style state constrained neuron (SCN) model for the design of processors in analog recurrent neural networks such as Hopfleld neural networks, cellular nonlinear networks for combinatorial optimization is described. The unconstrained neurons which have the free state variable, could be stable at any arbitrary point in the solution space or trapped by un-intentional effects. These may introduce errors. For the unconstrained network, the solution could be different from the expected one due to the discrepancy in the energy function of the network and the objective function to be optimized. In addition, if the state variable is limited by some neighboring saturated transistors, un-desirable results may be obtained. Gm C-style SCN model can ensure the convergence of the network and avoid discrepancy between the energy function of the network and the objective function. The state resistor is also eliminated in the Gm C model so that high cell-density can be achieved. Simulation results show that the proposed model is effective in significantly reducing optimization error.

Original languageEnglish
Pages (from-to)445-449
Number of pages5
JournalIEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Volume44
Issue number5
DOIs
StatePublished - 1997
Externally publishedYes

Fingerprint

Dive into the research topics of 'A state-constrained model for cellular nonlinear network optimization'. Together they form a unique fingerprint.

Cite this