Department Head (Machine Intellection), A*STAR Institute of Infocomm Research
Dr. Li Xiaoli is the Department Head and Principal Scientist of the Machine Intellection (MI) department at the Institute for Infocomm Research (I2R), A*STAR, Singapore. He also holds adjunct full professor position at School of Computer Science and Engineering, Nanyang Technological University. He has been a member of ITSC (Information Technology Standards Committee) from ESG Singapore and IMDA since 2020 and has served as joint lab directors with a few major industry partners.
Dr. Li also served as a health innovation expert panel member for the Ministry of Health (MOH), as well as an AI advisor for the Smart Nation and Digital Government Office (SNDGO), Prime Minister’s Office, highlighting his extensive involvement in key Government and industry initiatives.
His research interests include AI, data mining, machine learning, and bioinformatics. He has been serving as the Chair of many leading AI/data mining/machine learning related conferences & workshops (including KDD, ICDM, SDM, PKDD/ECML, ACML, PAKDD, WWW, IJCAI, AAAI, ACL, and CIKM). He currently serves as editor-in-chief of Annual Review of Artificial Intelligence, and associate editor of Knowledge and Information Systems, and Machine Learning with Applications (Elsevier).
Dr Li is a pioneer researcher in the following two domains:
1. Positive Unlabelled learning, with more than 3,000 citations and the term Positive Unlabelled Learning was coined in his paper,
2. A.I. based time series sensor data analytics for equipment health monitoring, with more than 3,000 citations (his top AI IJCAI 2015 paper has been cited more than 1,300 times).
He was one of the first researchers to formulate the sensor feature learning problem using deep neural networks. He led his team to win various top AI and data analytics international benchmark competitions and works closely with government agencies and industry partners across different verticals, e.g., bank and insurance, healthcare, aerospace, telecom, audit firm, transportation etc, to create social and economic impact.
Dr Li has published more than 320 peer-reviewed papers in top A.I., Data Mining, Machine Learning and Bioinformatics conferences and journals with more than 19,000 citations (more than 2,000 annual citations in recent years; H-index 69) and won ten best paper awards.
His global standing in the field of Computer Science has been acknowledged by his ranking at #713 among the Best Scientists by Research.com (https://research.com/u/xiaoli-li). Additionally, he has been recognized as one of the world's top 2% scientists in the AI domain by Stanford University.
Presentation Title: Revolutionizing Semiconductors: The Transformative Power of A.I.
The semiconductor industry is facing unprecedented challenges driven by the increasing complexity of manufacturing and design. Shrinking interconnect sizes and advanced packaging methods create challenges across the value chain. In this talk, we explore the transformative role of AI in addressing these challenges, with the goal of minimizing defects, reducing downtime, and streamlining design processes. We begin by delving into AI solutions tailored for manufacturing hurdles, then elaborate on the potential for AI to further enhance productivity. Our talk will focus on the following areas:
1. A.I.-Powered 3D Metrology: Our focus here is on 3D metrology and the detection of buried defects in 2.5D and 3D packaging. We demonstrate how new AI techniques such as Semi-Supervised, Active and Incremental learning can reduce the annotation requirements. We'll also share recent advancements in reducing the labor-intensive process of training these AI models.
2. Predictive Maintenance: We discuss how A.I. can be employed for predictive maintenance of manufacturing equipment, ensuring smoother operations and minimizing disruptions.
3. Design Automation: We demonstrate how A.I. can catalyze design acceleration on multiple fronts—process, packaging, and circuit design, through the use of neural surrogates and advanced inverse design techniques.
4. Future landscape of A.I. in the semiconductor industry: We elaborate how to uncover A.I.’s potential to enhance productivity even further. Our goal is to inspire innovative strategies and solutions for overcoming the industry's growing complexities and challenges.