Peter A. N. Bosman | Sightseeing along the Road to Evolutionary Intelligence
28 MARCH 2024
In this talk, I will present a general notion and key aspects of my personal long-term vision of Evolutionary Intelligence, being a mixture of evolutionary computation and machine learning, as well as present-day state-of-the-art practice and possibilities within this research area. This includes my research line on the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) family, showcasing its advantageous properties over classical "blind” Evolutionary Algorithms (EAs) by incorporating various machine learning techniques, as well as an example of real-world societal impact that we have been able to make through an application in medicine that led to clinical uptake at our partner institute Amsterdam UMC: automatically designing high-quality internal radiation treatment plans (brachytherapy) for prostate cancer. Besides this, I will provide an overview of the projects that I am currently involved in together with academic and industrial partners, highlighting both the fundamental and applied challenges that are being targeted.
Prof.dr. Peter A.N. Bosman is a group leader (of the group “Evolutionary Intelligence") at the Centrum Wiskunde & Informatica (CWI) in Amsterdam and a part-time professor (of Evolutionary Algorithms) at Delft University of Technology. He has a lifetime research focus on the design and application of highly scalable model-based evolutionary computation techniques, which includes his state-of-the-art research line on GOMEA, the Gene-pool Optimal Mixing Evolutionary Algorithm family. Building on this, he develops innovative solutions for real-world applications, many of which are in the medical domain, and studies novel combinations of evolutionary algorithms and machine learning techniques. He has won many awards for fundamental papers and real-world applications alike, especially in the medical domain, including 9 best paper awards and 2 awards for obtaining real-world human-competitive awards with EAs. He is currently chair of SIGEVO, the ACM special interest group on Genetic and Evolutionary Computation and was formerly an officer, executive board, and business committee member of SIGEVO., as well as program committee member of various major conferences and journals in the EA field and related fields. Through numerous research grants, he collaborates with many partners in both academia and industry.