Keynote Speakers

Prof. Dr. Loo Chu Kiong

Department of Artificial Intelligence
Faculty of Computer Science and Information Technology
Universiti Malaya, Malaysia

Continual Machine Learning: Overview & Challenges

Humans can continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as continual learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. On the other hand, continual learning capabilities are crucial for computational learning systems and autonomous robots interacting in the real world and processing continuous streams of information. However, continual machine learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions leads to catastrophic forgetting or interference. This talk is about the research journey in the quest for continual machine learning. It will encompass several aspects of research and development of neural networks inspired by Adaptive Resonance Theory and related continual machine learning models.

Prof. Dr. Loo is a full Professor at the Department of Artificial Intelligence, Faculty of Computer Science & Information Technology, Universiti Malaya. His research in continual lifelong learning has contributed to solving the “catastrophic forgetting” in machine learning. He has conducted research in brain-inspired robotics and hybrid intelligence for healthcare under the Georg Forster Fellowship award, in Germany and the JSPS fellowship award, in Japan. From these research activities, he has published more than 200 peer-reviewed journal and conference papers on neurorobotics and machine intelligence. He has been a visiting professor at Tokyo Metropolitan University, University of Prefectural Osaka University, Japan, and King Mongkut's Institute of Technology Ladkrabang, Thailand.

Prof.Dr. A.E. Eiben

Vrije Universiteit Amsterdam,The Netherlands
University of York, United Kingdom

From Robot Evolution to Artificial Life

In this talk I introduce the notion of artificial evolution and explain how it can be applied to developing intelligent robots. I demonstrate that evolution can deliver good brains (controllers) as well as good bodies (morphologies) and give insights into the “Robot Baby Project” that showcased the reproduction of two physical robots for the first time. I present the concept of the Evolution of Things and outline its benefits for engineering as well as for fundamental research. I argue that constructing systems of self-reproducing machines will lead to an exciting mix of evolutionary computing, artificial intelligence, robotics, and artificial life with new challenges and opportunities.

A.E. (Guszti) Eiben has a Masters in Mathematics (ELTE, Budapest) and a PhD in Computer Science (TU Eindhoven). Currently he is a professor of Artificial Intelligence on the Vrije Universiteit Amsterdam and visiting professor at the University of York. He is one of the early birds of evolutionary computing in Europe who literally wrote the book and an expert in evolutionary robotics. His main research concerns robots that can reproduce, evolve, and learn. His work is published in top journals (Nature, Science) and extensively covered by popular media (e.g., WIRED, New Scientist) in 10 countries. His long- term goal is to demonstrate that artificial evolution can develop artificial intelligence and to understand the evolutionary interplay between the body and the brain.

Professor Aleksander Byrski

AGH University of Science and Technology, Poland

Authorized metaheuristics in action

Several years ago I participated in a fine lecture by Kenneth Sorensen about flaws and misuse of metaheuristics. It is impossible to blame the speaker for anyting, there are many of us running headlong into mimicking new species of animals in an algorithm, treating the process of creation of new metaheuristics as the only valuable goal of the research. In the course of this lecture I would like to remind about the most important theses of Sorensen, refer to the true motivation for using the metaheuristics and point out several features of the existing metaheuristics which make them especially useful for realization of optimization of hard problems. I will refer to theoretical background, naturalness of some methods, implementation-related features and hybridization. The goal of the lecture is to build onto what my predecessor said, paving the way for "authorized" development of metaheuristics which will be truly functional and make sense from scientific point of view.

Aleksander Byrski (Ph.D. 2007, D.Sc. 2013 - AGH University of Science and Technology, Full Professor Title - President of Poland) works at the AGH University of Science and Technology in Krakow, the biggest Technical University in Poland. He is interested mainly in metaheuristic-based optimization, in particular novel techniquest related to agent-oriented inspirations, efficient and efficacious implementation of metaheuristics, novel ideas for metaheuristics inspirations. He holds a position of Deputy Director of the Institute of Computer Science AGH and V-ce Chairman of the Polish Academy of Sciences Computer Science Committee.

Professor Diego Paez-Granados

Head of Spinal Cord Injury & Artificial Intelligence - SCAI Lab, ETH Zurich, Switzerland
Group Leader: Digital Health Care and Rehabilitation, SPF, Nottwil, Switzerland

The Future of Transparent AI in Healthcare and Assistive Technology

This talk highlights the gap between AI advancements and long-term healthcare support, while presenting our vision for the future of AI in Health Supporting Systems. Focusing on chronic conditions, particularly spinal cord injuries (SCI), our research group explores transparent AI models that integrate medical staff in decision-making.
I will present our vision of modeling the human body using biosignals and behavioral responses for disease onset detection, emphasizing interpretable models and graphical model based learning.
Specifically, I will focus on the importance of interpretable models and demonstrate how graphical models and explainable regressions and classifications are fundamental for understanding of disease progression and treatment effects.
By addressing these key areas of research, we aim to bridge the gap between AI advancements and long-term healthcare support, ultimately paving the way for a future where AI plays a pivotal role in health prevention, disease prediction, and personalized treatment strategies.
Moreover, I will explore our vision of sensor fusion, encompassing both body and environmental data, to enhance life for individuals with mobility impairments in a seamless unobtrusive manner that complement their life to.

Dr. Paez is the Head of the SCAI Lab at ETH Zürich and Swiss Paraplegic Research (SPF) in Switzerland. With a focus on personalized healthcare, his lab utilizes advanced machine learning techniques and wearable sensing to develop assistive decision-making systems that model disease onset and develop digital biomarkers.
Passionate about enhancing healthcare, Dr. Paez is dedicated to creating patient digital twins and leveraging them to develop preventive technologies that support healthcare workers and caregivers. His diverse research interests span human modeling, human-robot interaction control, explainable models for machine learning in healthcare applications, and biosignal processing.
Dr. Paez holds a PhD in Bioengineering and Robotics from Tohoku University, Japan, and has contributed his expertise to renowned research institutions including the University of Tsukuba and EPFL, Switzerland. Additionally, he holds a visiting faculty position at the Cybernetics Research Institute in Japan.
Driven by his research and patent achievements, Dr. Paez has co-founded Qolo Inc., a startup based in Japan specializing in personal mobility and rehabilitation devices, as well as DAAV, a Swiss company focusing on assistive robotics for mobility.