PhD: MACHINE-LEARNING-BASED TESTING AND TEST GENERATION FOR ANALOG/MIXED-SIGNAL ICS

12 July 2019

Get in touch!

Interested?

For more information, please contact Prof. dr. ir. Georges Gielen, tel.: +32 16 32 40 76, mail: georges.gielen@kuleuven.be.

You can apply for this job no later than August 10, 2019 via the online application tool.

KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at diversiteit.HR@kuleuven.be.

Apply before 10 August 2019

This PhD will investigate and explore the emerging capabilities of novel techniques from machine learning and artificial intelligence (AI) towards the efficient testing and test generation for analog integrated circuits. Detecting outlying behavior will be a major focus to maximize test coverage. Also, solutions towards real-time monitoring and signal interpretation in the edge will be investigated.

This PhD research will take place at the ESAT-MICAS (Microelectronics and Sensors) research group of KU Leuven Department of Electrical Engineering (ESAT), that is internationally renowned for its research on integrated electronics. Academic supervisor will be Prof. Georges Gielen, who is an expert in design and design automation of analog/mixed-signal integrated circuits.

Website unit

Project

Many emerging electronic applications, such as the internet of things (IoT) or smart autonomous systems, rely on analog and mixed-signal (AMS) circuits to interface with the physical world (e.g. sensors, radios,etc.). Examples are fields like automotive, biomedical, industry 4.0, etc. Computation in the edge and embedded intelligence are becoming standard practice. In addition, these applications come with extremely demanding reliability and robustness requirements: the circuits may not fail undetectedly. This must be addressed at IC design time (pre-fabrication), at IC test time (post-fabrication) and at run time (during IC usage). Due to their nature and sensitivity, however, the analog parts of AMS systems require significantly more testing effort, compared to their size.


This PhD will therefore investigate and explore the emerging capabilities of novel techniques from machine learning and artificial intelligence (AI) towards the efficient testing and test generation for analog integrated circuits. Detecting outlying behavior will be a major focus to maximize test coverage. Also, solutions towards real-time monitoring and signal interpretation in the edge will be investigated.


The PhD work will involve the development of novel machine learning/AI techniques and algorithms, and their application to the testing of analog/mixed-signal electronic integrated circuits.

Profile

Required background: Master in ElectricalEngineering or Master in Computer Science with proven knowledge of programming/CAD and of analog/mixed-signal integrated circuits.

Offer

The position offers a PhD scholarship for 4 years.