Enrichment of limited training sets in machine-learning-based analog/RF Test

Haralampos-G Stratigopoulos (1) , Salvador Mir (1) , Y. Makris (2)

1 TIMA - Techniques de l'Informatique et de la Microélectronique pour l'Architecture des systèmes intégrés
2 Department of Electrical Engineering [Yale University]

This paper discusses the generation of information-rich, arbitrarily-large synthetic data sets which can be used to (a) efficiently learn tests that correlate a set of low-cost measurements to a set of device performances and (b) grade such tests with parts per million (PPM) accuracy. This is achieved by sampling a non-parametric estimate of the joint probability density function of measurements and performances. Our case study is an ultra-high frequency receiver front-end and the focus of the paper is to learn the mapping between a low-cost test measurement pattern and a single pass/fail test decision which reflects compliance to all performances. The small fraction of devices for which such a test decision is prone to error are identified and retested through standard specification-based test. The mapping can be set to explore thoroughly the trade-off between test escapes, yield loss, and percentage of retested devices.

Mots clés: RF-applications; Analogue test

Domaines: Micro et nanotechnologies/Microélectronique

Haralampos-G Stratigopoulos, Salvador Mir, Y. Makris. Enrichment of limited training sets in machine-learning-based analog/RF Test. Design, Automation and Test in Europe Conference (DATE'09), Apr 2009, Nice, France. pp.1668 - 1673. ⟨hal-00418408⟩