Quick Navigation:
Speaker: Professor Marjan Mernik, University of Maribor, Slovenia
Date & Time: 17 March 2026, Tuesday, 3-5pm
Venue: Engineering Auditorium, National University of Singapore
Abstract:
Evolutionary algorithms mimic natural processes such as selection, crossover, and mutation to solve a wide range of optimization problems. Effective application of these algorithms requires a solid understanding of the various selection, crossover, and mutation operators. However, exploration and exploitation are fundamental processes—and arguably the most critical concepts—for any search algorithm. Despite their importance, these concepts are not yet well understood among many researchers and practitioners. Furthermore, the direct measurement of exploration and exploitation remains an open problem in evolutionary computation.
This talk first introduces the basic components of evolutionary algorithms, highlights common issues and mistakes encountered by inexperienced users, and discusses their diverse applications. In the second part, a novel direct measure of exploration and exploitation based on attraction basins is presented. Attraction basins are regions of a search space in which each region contains a point, called an attractor, toward which neighbouring points tend to evolve. Each search point can therefore be associated with a specific attraction basin. If a newly generated search point belongs to the same attraction basin as its parent, the search process is considered exploitation; otherwise, it is classified as exploration.
In the final part, the talk demonstrates how the newly developed exploration and exploitation measures can be used to analyze and compare different evolutionary algorithms.
*No registration required.
Speaker: Professor YAO Xin, Vice-President (Research and Innovations) & Tong Tin Sun Chair Professor of Machine Learning, Lingnan University, Hong Kong, China
Date & Time: 22 April 2026, Wednesday, 10:05-10:50am
Venue: Ngee Ann Kong Si Auditorium, School of Accountancy, Singapore Management University
Abstract:
Trustworthiness is a critical issue in artificial intelligence (AI), especially for real-world applications. It is impossible to deloy AI in the real world without its being trustworthy. However, the connotation and extension of AI trustworthiness are not entirely clear. There has not been a single definition that is accepted by all researchers. Nevertheless, the vast majority of researchers agree that AI trustworthiness should include at least accuracy, reliability, robustness, safety, security, privacy, fairness, transparency, controllability, maintainability, etc. This talk starts from a brief recall of trustworthy systems in the literature. It tries to understand any potential difference between classical trustworthy systems and modern-day trustworthy AI. It argues that AI ethics is a crucial part of trustworthy AI, which was not featured in classical trustworthy systems. The talk then presents a short summary of AI ethics, and dives a little deeper into the fairness and explainability issues of machine learning models. It demonstrates that many aspects of AI ethics, such as fairness and explainability, are inherently multi-dimensional, which cannot be defined completely and accurately by any single metrics. Multi-objective thinking is essential in AI ethics. While a weighted sum approach can convert a multi-objective problem into a single objective one, this talk offers an alternative and illustrates how multi-objective evolutionary learning can be used to enhance fairness and explainability of machine learning models.
*Registration required (by 15 April 2026, Wednesday, 11:59 pm), click here.
Speaker: Professor ONG Yew Soon, President's Chair Professor, College of Computing & Data Science & Professor (Cross Appointment), School of Physical and Mathematical Science, Nanyang Technological University, Singapore
Date & Time: 22 April 2026, Wednesday, 10:50-11:35am
Venue: Ngee Ann Kong Si Auditorium, School of Accountancy, Singapore Management University
Abstract:
Artificial intelligence is reshaping how we explore ideas, understand information, and make decisions. This talk examines how AI language models are transforming research and data analysis—accelerating insight discovery, lowering barriers to working with complex information, and expanding access to knowledge across disciplines and backgrounds. We shall reflect on how this shift is opening new possibilities in learning, creativity, and collaboration, while also considering the challenges, limitations, and responsibilities that accompany the growing use of AI. Whether you are a researcher, professional, educator, or lifelong learner, this session hopes to offer a fresh perspective on the evolving role of AI in how we learn, think, and discover.
*The speaker of this talk is IEEE Distinguished Lecturer.
*Registration required (by 15 April 2026, Wednesday, 11:59 pm, same registration link as Prof YAO Xin's seminar), click here.
21 - 26 June, Maastricht, The Netherlands
Conference website: https://attend.ieee.org/wcci-2026/