Sunday, April, 22nd

VTS’18 is offering 2 half-day TTEP tutorials, one in the morning and one in the afternoon, for which a separate registration fee is required. Attendees who register for the tutorials may select either one or both of the offerings.
All tutorials qualify for credit towards IEEE TTTC certification under the TTEP program. Attendees of tutorials receive study material, handouts, breakfast and coffee breaks. The study material includes copies of the presentation and bibliographical material, and, when applicable, a relevant textbook (textbooks are provided to attendees who register at IEEE/CS member or non-member rates).

Morning Tutorial – Machine Learning and Its Applications in Test

In this tutorial, we will start by covering the basics of machine learning. We will proceed to give a brief overview of the new and exciting field of deep learning. We will show how easy it is to try using machine learning and deep learning, thanks to powerful, free libraries. After offering the required background in machine learning, we will review several important papers in the field of DFT, diagnosis, yield learning, and root cause analysis, which use machine learning algorithms for solving various problems. Finally, we will propose future research directions in the area of testing, where we think machine learning (especially deep learning) can make a big impact.

Afternoon Tutorial – Learning Techniques for Reliability Monitoring, Mitigation and Adaptation

With increasing the complexity of digital systems and the use of advanced nanoscale technology nodes, various process and runtime variabilities threaten the correct operation of these systems. The interdependence of these reliability detractors and their dependencies to circuit structure as well as running workloads makes it very hard to derive simple deterministic models to analyze and target them. As a result, machine learning techniques can be used to extract useful information which can be used to effectively monitor and improve the reliability of digital systems. These learning schemes are typically performed offline on large data sets in order to obtain various regression models which then are used during runtime operation to predict the health of the system and guide appropriate adaptation and countermeasure schemes.

Registration

To register to the tutorials please visit the Registration page.