Using neural networks and 3D polynomial interpolation for the study of probe yield vs. E-test correlation. Application to sub-micronics mixed-signal technology

Author

Montull, J. Ignacio Alonso ; Ortega, Carlos ; Sobrino, Eliseo

Author_Institution

Microelectron. Group, Lucent Technol., Madrid, Spain

fYear

1999

fDate

1999

Firstpage

197

Lastpage

201

Abstract

In the present paper we propose the use of neural networks for statistical modelling of data, as well as the use of 3D surface in order to visualise results in a very intuitive way. The scope of the paper is to present a method for extracting qualitative information from the confrontation of yield and E-test data in order to easily identify best process conditions and potential process marginality issues. The neural network approach is a new way to face determining the huge amount of raw data that yield analysis involves in the microelectronics industry

Keywords

correlation methods; integrated circuit modelling; integrated circuit yield; interpolation; mixed analogue-digital integrated circuits; neural nets; production engineering computing; statistical analysis; 3D polynomial interpolation; 3D surface; E-test correlation; best process conditions; microelectronics industry; neural networks; probe yield; process marginality issues; qualitative information; statistical modelling; sub-micronics mixed-signal technology; yield analysis; Data visualization; Genetic expression; Interpolation; Microelectronics; Multilayer perceptrons; Network topology; Neural networks; Polynomials; Probes; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Semiconductor Manufacturing Conference and Workshop, 1999 IEEE/SEMI

Conference_Location

Boston, MA

ISSN

1078-8743

Print_ISBN

0-7803-5217-3

Type

conf

DOI

10.1109/ASMC.1999.798222

Filename

798222