A Machine Learning-based Test Program Quality Tool for Automotive Microcontrollers

In Infineon, production testing is an important aspect, during which thousands of data are stored, the purpose of this thesis is to make use of these data to build a quality gate tool based on machine learning techniques in order to improve testing quality. In fact, tests in the production flow involves two important sequential phases, the front-end and the back end-testing. In this thesis, we study the possibility of predicting the final BE label of the chips based on the FE tests.