Mar 11 (Fri) @2:00pm: "Domain-Specific Machine Learning - A Human Learning Perspective," Chuanhe (Jay) Shan, ECE PhD. Defense

https://ucsb.zoom.us/j/82124649449

Abstract

This dissertation focuses on Domain-Specific Machine Learning (DSML) with applications in the semiconductor industry. We first illustrate characteristics of DSML in view of semiconductor design and test processes, where a task is usually carried out in an iterative fashion. We introduce a new concept called Local No-Free-Lunch (Local NFL) to characterize the learning problem in an iteration, where one learns from the data in the current iteration and tries to predict the outcome in the next iteration. A consequence of Local NFL is that optimization of a learning model is no longer as critical in DSML as that in traditional Machine Learning. 

To study how to build a practical DSML solution, we take Wafer Map Pattern Recognition (WMPR) as the application context. Historically, WMPR is an important problem to solve for semiconductor manufacturers, where wafer failing patterns are used to guide their yield improvement effort. In recent years, fabless companies became interested in the problem because understanding wafer patterns can help them communicate more effectively with the manufacturers. In the past, prior works treated WMPR as solving a multi-class classification problem. However, in view of DSML, we argue that a multi-class classifier is not what is needed for building a practical DSML solution. 

We then develop the requirements and constraints for building a practical DSML solution. From there, we reach a list of tool capabilities to be supported by the solution. To enable these capabilities, we develop novel learning techniques for performing various analyses on wafer maps. Based on the enabled capabilities, a novel methodology is introduced. Given a sequence of wafer maps, this methodology enables a user to quickly see what potential patterns are in the sequence and based on their own perspective, to make a final decision to classify them. 

This methodology enables building a practical DSML solution that helps a user answer two main questions in each iteration: (1) Is there a wafer pattern indicating a potential yield issue? 2) If yes, has this pattern occurred previously? An important aspect of the solution is that it enables a user to quickly grasp what crucial information is contained in the data and facilitates them to make a final classification decision. The solution does not make a final decision for them. From this angle, the focus of a DSML solution is on understanding of the data, rather than on optimization of a learning model.   

Bio

Chuanhe (Jay) Shan is a 8th year PhD. candidate at UCSB, where he also received his B.S. and M.S. in Computer Engineering. During his graduate studies, he interned for a combined 15 months at NXP and GlobalFoundries. During his stay at NXP, he developed and deployed software tools aimed at improving cost and quality using data analytics. In GlobalFoundries, Jay developed and deployed data-driven tools for improving Diagnosis. Jay has co-authored 10 publications during his graduate studies, 3 of which won Best Paper Awards (VTS 2016, VLSI-DAT 2019, & ITC 2020).  His research focuses on the application of domain-specific machine learning (DSML) in the semiconductor industry. Jay is also a member of the Intelligent Engineering Assistant project (IEA, link: https://iea.ece.ucsb.edu/). The project focuses on developing DSML technologies to assist the engineers in understanding their own data.

Hosted by: Professor Li-C. Wang

Submitted by: Chuanhe (Jay) Shan <chuanheshan@ucsb.edu>