No. 2 - Intepretable Artificial Intelligence
17 June 2019 14:00 - 15:00, Room IT 405, ICT Building, Mahidol University (Salaya)
Title: Interpretable Artificial Intelligence
Abstract: Interpretable artificial intelligence (IAI) refers to techniques which can be trusted and easily understood by humans. Unlike the concept of ‘black box’, IAI can be used to implement a social right to explanation i.e. to explain why an AI arrives to a specific decision. A technical challenge of explaining AI decisions is known as the interpretability problem. One possible approach for handling it is to carefully design and develop AI w.r.t. formal syntax and semantics. In this talk, we will introduce the basics of computational logic (the notions of syntax, semantics, and proof theory) and its relationship to knowledge representation formalisms. We will also investigate the standard inferences and relate their computations to the transparency of AI decisions.
Bio: Teeradaj Racharak is an assistant professor in the field of artificial intelligence at Japan Advanced Institute of Science and Technology (JAIST). Prior to that, he did his Ph.D. in description logic under the supervision of professor Satoshi Tojo and his master in logic programming under the supervision of professor Phan Minh Dung. Apart from his studies in computational logic, he is an open-minded software engineer and interested in many things related to artificial intelligence and software development methodologies. His research interest is centered on formal development toward human intelligence i.e. how a machine can ‘learn’ and ‘reason’ like a human? In particular, he has been studying to address the following research areas: (1) machine learning, (2) computational logic, and (3) their applications to natural language understanding.
No. 1 - The future of software defect prediction and software quality
11 June 2019 13:30 - 14:30, Room IT 405, ICT Building, Mahidol University (Salaya)
Title: Explainable Artificial Intelligence to Predict Future Software Defects
Abstract: With the rise of software systems ranging from personal assistance to nation’s facilities, software defects become more critical concerns as they can cost millions of dollar as well as impact human lives. Yet, at the breakneck pace of rapid software development settings (like Agile/DevOps paradigm), the Quality Assurance (QA) practices nowadays are still time-consuming. Currently, I’m leading a research program to develop AI to predict future software defects and explain why they are defective in order to optimize the limited QA resources and develop the most effective quality improvement plans. This research project is expected to provide significant benefits including the reduction of software defects and operating costs, while accelerating development productivity.
Bio: Dr. Chakkrit (Kla) Tantithamthavorn is an Assistant Professor in Faculty of Information Technology, Monash University, Melbourne, Australia (a research-intensive university in the World’s Top 100 Universities). His current research focuses on Explainable AI in Software Engineering. His work has been published at top-tier software engineering venues, such as IEEE Transactions on Software Engineering (TSE), Empirical Software Engineering (EMSE), and the International Conference on Software Engineering (ICSE). Please contact me if you want to do world-class research on the development of AI technologies to improve software quality and productivity.
Abstract: Software is a byproduct of human activities. To strive for the successful completion of a software product, software development requires deep collaboration and interactions among software practitioners, especially for globally-distributed software development teams. Due to the continuously growing size of development teams and software products, collaboration management becomes a crucial concern. For example, poor collaboration in software development processes may lead to poor software quality. However, good practices still remains an elusive goal. Therefore, Dr Thongtanunam’s research focuses on incorporating various sources of development activities, gleaning actionable insights for software engineering management, and providing tool support for software practitioners with the aim of improving software quality. In this talk, Dr Thongtanunam will present her empirical studies which highlight the impact of code review practices on software quality and discuss some of her proposed tool support (e.g., a reviewer recommendation algorithm).
Bio: Dr Patanamon Thongtanunam is a lecturer at School of Computing and Information Systems (CIS), the University of Melbourne (The number 1 university in Australia and Top 32 university in the world). Her primary research goals are directed towards data-driven software engineering, i.e., uncovering empirical evidence and extracting knowledge from data recorded in software repositories by using statistical analysis. Her research has been published at top-tier software engineering venues like International Conference on Software Engineering (ICSE) and Journal of Empirical Software Engineering (EMSE). More about Dr Thongtanunam and her work is available online at http://patanamon.com.