Artificial-Neural-Network Prediction of Device Behaviors in Submicron MOS Transistors

Shen Li Chen; Ying Der Chen

doi:10.4028/www.scientific.net/AMR.634-638.2442

Paper Titles

Effect of Additive on Phase Composition and Microstructure of Silica Brick Matrix
p.2419

Analytical Solutions for Laminated Transversely Isotropic Magnetoelectroelastic Plates
p.2425

Anisotropy in Third-Order Nonlinear Optical Susceptibility of the Stretch-Oriented Chrysophenine-Doped Poly(vinyl alcohol) Films
p.2432

Calculation of the Interaction Forces between Superconductor and Permanent Magnet Using Equivalent Current Loops in Zero Field Cooling
p.2436

Artificial-Neural-Network Prediction of Device Behaviors in Submicron MOS Transistors
p.2442

Charge Programming and Erasing Characteristics of the Submicron Stacked-Gate Flash Cells
p.2446

Effect of Ca Doping on Crystal Structure of the Misfit-Layered Bi-Sr-Co-O Thermoelectric Materials
p.2450

Effects of Surfactants on Particle Size and Luminescence Properties of Ca_1.98MgSiO₅:Eu²⁺_0.02 Phosphor Prepared by Sol-Gel Method
p.2454

Effects of Annealing in Air on Structure and Properties of Al Films Prepared by Thermal Evaporation
p.2458

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 634-638Artificial-Neural-Network Prediction of Device...

Artificial-Neural-Network Prediction of Device Behaviors in Submicron MOS Transistors

Abstract:

A new technique is presented for modeling submicron MOSFET devices and predicting the MOSFET device behaviors by using fuzzy theory and artificial neural network (ANN). The power of ANNs used as a realization of I-V characterizations is demonstrated on the submicron MOS transistors. The prediction results are compared with experimental data of the actual devices and obtained a good agreement under different bias situations.