Li-Chung Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Li-Chung Wang has a total of 159 co-authors. Here are the top co-authors by number of shared publications:
Magdy S. Abadir
University of California, Santa Barbara, USA
29 shared publicationsKwang-Ting Cheng
23 shared publicationsNik Sumikawa
NXP Semiconductor, Chandler, AZ, 85224
12 shared publicationsPouria Bastani
Intel Corporation, USA
11 shared publicationsDragoljub Drmanac
Univ. of California, Santa Barbara, CA, USA
9 shared publicationsM.S. Abadir
9 shared publications
Latest Publications
- Open Access
- 9 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
LLM-Assisted Analytics in Semiconductor Test (Invited)
The emergence of Large Language Models (LLMs) has impacted our perspective on applying Machine Learning (ML) in semiconductor test. This paper shares our experience in leveraging the power of LLMs to build an AI agent for test data analytics. We advocate for an end-to-end approach where the Knowledge Graph (KG) plays a central role. Using wafermap analytics as an example, we highlight the key ideas behind developing the LLM-assisted AI agent named IEA-Plot, and discuss its practical applications.
- 9 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessLLM-Assisted Analytics in Semiconductor Test (Invited)
The emergence of Large Language Models (LLMs) has impacted our perspective on applying Machine Learning (ML) in semiconductor test. This paper shares our experience in leveraging the power of LLMs to build an AI agent for test data analytics. We advocate for an end-to-end approach where the Knowledge Graph (KG) plays a central role. Using wafermap analytics as an example, we highlight the key ideas behind developing the LLM-assisted AI agent named IEA-Plot, and discuss its practical applications.
- 16 March 2019
- Published by Springer Nature
- p. 375-399
Learning from Limited Data in VLSI CAD
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 15, 1-10
Concept Recognition in Production Yield Data Analytics
An analytic process is iterative between two agents, an analyst and an analytic toolbox. Each iteration comprises three main steps: preparing a dataset, invoking an analytic tool, and evaluating the result, where dataset preparation and result evaluation, conducted by the analyst, are largely domain-knowledge driven. In this work, the focus is on automating the result evaluation step. In particular, we consider the problem to recognize plots that are deemed interesting by an analyst. We propose a methodology to learn such analyst's intent based on Generative Adversarial Networks (GANs) and demonstrate its applications in the context of production yield optimization using data collected from several product lines.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 15, 1-10
Concept Recognition in Production Yield Data Analytics
An analytic process is iterative between two agents, an analyst and an analytic toolbox. Each iteration comprises three main steps: preparing a dataset, invoking an analytic tool, and evaluating the result, where dataset preparation and result evaluation, conducted by the analyst, are largely domain-knowledge driven. In this work, the focus is on automating the result evaluation step. In particular, we consider the problem to recognize plots that are deemed interesting by an analyst. We propose a methodology to learn such analyst's intent based on Generative Adversarial Networks (GANs) and demonstrate its applications in the context of production yield optimization using data collected from several product lines.
- Open Access
A Concept Learning Tool Based On Calculating Version Space Cardinality
In this paper, we proposed VeSC-CoL (Version Space Cardinality based Concept Learning) to deal with concept learning on extremely imbalanced datasets, especially when cross-validation is not a viable option. VeSC-CoL uses version space cardinality as a measure for model quality to replace cross-validation. Instead of naive enumeration of the version space, Ordered Binary Decision Diagram and Boolean Satisfiability are used to compute the version space. Experiments show that VeSC-CoL can accurately learn the target concept when computational resource is allowed.
Open AccessA Concept Learning Tool Based On Calculating Version Space Cardinality
In this paper, we proposed VeSC-CoL (Version Space Cardinality based Concept Learning) to deal with concept learning on extremely imbalanced datasets, especially when cross-validation is not a viable option. VeSC-CoL uses version space cardinality as a measure for model quality to replace cross-validation. Instead of naive enumeration of the version space, Ordered Binary Decision Diagram and Boolean Satisfiability are used to compute the version space. Experiments show that VeSC-CoL can accurately learn the target concept when computational resource is allowed.
- 26 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 36 (6) , 885-898
Experience of Data Analytics in EDA and Test—Principles, Promises, and Challenges
Applying modern data mining in electronic design automation and test has become an area of growing interest in recent years. This paper reviews some of the recent developments in the area. It begins by introducing several key concepts in machine learning and data mining, followed by a review of different learning approaches. Then, the experience of developing a practical data mining application is described, including promises demonstrated through positive results based on industrial settings and challenges explained in the respective application contexts. Future research directions are summarized at the end.
- 26 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 36 (6) , 885-898
Experience of Data Analytics in EDA and Test—Principles, Promises, and Challenges
Applying modern data mining in electronic design automation and test has become an area of growing interest in recent years. This paper reviews some of the recent developments in the area. It begins by introducing several key concepts in machine learning and data mining, followed by a review of different learning approaches. Then, the experience of developing a practical data mining application is described, including promises demonstrated through positive results based on industrial settings and challenges explained in the respective application contexts. Future research directions are summarized at the end.
- 20 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test
- Vol. 33 (6) , 96
ITC and the Future of Test—We've Won
Discusses the future of testing from the perspective of the International Test Conference sponsors.
- 20 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test
- Vol. 33 (6) , 96
ITC and the Future of Test—We've Won
Discusses the future of testing from the perspective of the International Test Conference sponsors.
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Consistency in wafer based outlier screening
Outlier screening is a popular approach for testing automotive products. In practice, developing an outlier model can be subjective, making justification of the model challenging. In this paper we propose a new concept called Consistency which provides a data-driven objective way to assess an outlier model. We study the development of outlier models in view of this new model consistency concept and report experimental findings on an automotive product line.
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Consistency in wafer based outlier screening
Outlier screening is a popular approach for testing automotive products. In practice, developing an outlier model can be subjective, making justification of the model challenging. In this paper we propose a new concept called Consistency which provides a data-driven objective way to assess an outlier model. We study the development of outlier models in view of this new model consistency concept and report experimental findings on an automotive product line.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Generalization of an outlier model into a “global” perspective
In this work, we study the generalization of an outlier model from two perspectives, temporal and spatial. We show that model generalization with existing distribution-based outlier analysis methods can vary significantly. We then propose a “big data” outlier analysis approach together with a probability-based outlier evaluation for improving model generalization. Experiments are conducted based on two automotive product lines to explain the concepts and demonstrate the effectiveness of the proposed approach.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Generalization of an outlier model into a “global” perspective
In this work, we study the generalization of an outlier model from two perspectives, temporal and spatial. We show that model generalization with existing distribution-based outlier analysis methods can vary significantly. We then propose a “big data” outlier analysis approach together with a probability-based outlier evaluation for improving model generalization. Experiments are conducted based on two automotive product lines to explain the concepts and demonstrate the effectiveness of the proposed approach.
- 1 June 2015
- Published by Academy of Management in Academy of Management Discoveries
- Vol. 1 (1) , 91-116
The Team Descriptive Index (TDI): A Multidimensional Scaling Approach for Team Description
The literature on teams is filled with many alternative team type taxonomies, and the persistence of so many conflicting taxonomies serves as evidence for the lack of consensus in the field about how to describe and differentiate teams in any standardized way. This paper presents the Team Descriptive Index (TDI) as an approach for rigorous team description based upon the Three-Dimensional Team Scaling Model (3DTSM) developed by Hollenbeck, Beersma, and Schouten (Academy of Management Review, 37, 92–106). The use of a continuous scaling approach to team description eliminates the need for researchers to force the teams they study into discrete categorical types that, more often than not, fail accurately to capture their nature in a precise way. We report the results of five different studies that provide construct validation evidence for a set of standardized measures for the 3DTSM with diverse samples that reflect the wide variety of contexts in which teams are studied.
- 1 June 2015
- Published by Academy of Management in Academy of Management Discoveries
- Vol. 1 (1) , 91-116
The Team Descriptive Index (TDI): A Multidimensional Scaling Approach for Team Description
The literature on teams is filled with many alternative team type taxonomies, and the persistence of so many conflicting taxonomies serves as evidence for the lack of consensus in the field about how to describe and differentiate teams in any standardized way. This paper presents the Team Descriptive Index (TDI) as an approach for rigorous team description based upon the Three-Dimensional Team Scaling Model (3DTSM) developed by Hollenbeck, Beersma, and Schouten (Academy of Management Review, 37, 92–106). The use of a continuous scaling approach to team description eliminates the need for researchers to force the teams they study into discrete categorical types that, more often than not, fail accurately to capture their nature in a precise way. We report the results of five different studies that provide construct validation evidence for a set of standardized measures for the 3DTSM with diverse samples that reflect the wide variety of contexts in which teams are studied.
- Open Access
- 29 March 2015
- Published by Association for Computing Machinery (ACM)
- p. 57-64
Machine Learning in Simulation-Based Analysis
This paper describes two separate learning flows for improving the efficiency of simulation-based design analysis. Machine learning concepts and methods are explained in the context of realizing the two learning flows. Experimental results are presented to demonstrate their feasibility. Generality of the proposed learning flows is illustrated using the kernel-based learning concept.
- 29 March 2015
- Published by Association for Computing Machinery (ACM)
- p. 57-64
Open AccessMachine Learning in Simulation-Based Analysis
This paper describes two separate learning flows for improving the efficiency of simulation-based design analysis. Machine learning concepts and methods are explained in the context of realizing the two learning flows. Experimental results are presented to demonstrate their feasibility. Generality of the proposed learning flows is illustrated using the kernel-based learning concept.