Plenary Talk 1
Session Chair: Jim Keller, Monday, July 3, 2023 at 9:00:00 AM CDT – 10:00:00 AM CDT Zurich D
- Pioneer Awardee 2023 (60m)
- Stephanie Forrest
Title: The Biology of Software
Abstract: Computer programmers like to think of software as the product of intelligent design, carefully crafted to meet well-specified goals. In reality, large software systems evolve inadvertently through the actions of many individual programmers, often leading to unanticipated consequences. Because software is subject to constraints similar to those faced by evolving biological systems, we have much to gain by viewing software through the lens of evolutionary biology. The talk will highlight research applying the mechanisms of evolution quite directly to software, including repairing bugs and optimizing GPU codes. These results have implications for how we think more generally about engineering complex systems that are subject to evolutionary pressures and engineering constraints.
Bio: Stephanie Forrest
Stephanie Forrest is Professor of Computer Science at Arizona State University, where she directs the Biodesign Center for Biocomputation, Security and Society. Her interdisciplinary research focuses on the intersection of biology and computation, including cybersecurity, software engineering, evolutionary computation, and biological modeling. Prior to joining ASU in 2017, she was a Distinguished Professor at the University of New Mexico and served for 5 yers as Dept. Chair. She is a member of the Santa Fe Institute External Faculty, where she has also served as co-Chair of its Science Board and Interim VP for Academic Affairs. She spent 2013-2014 at the U.S. Dept. of State as a Senior Science Advisor for cyberpolicy. She was educated at St. John’s College (B.A.) and the University of Michigan (M.S. and Ph.D. in Computer Science).
Some of her awards include: The 2023 IEEE Computational Intelligence Pioneer Award; The 2020 Test of Time Award from the IEEE Security and Privacy Symposium; The 2019 Most Influential Paper Award from the International Conference on Software Engineering, the Santa Fe Institute Stanislaw Ulam Memorial Lectures (2013), the ACM/AAAI Allen Newell Award (2011), and the NSF Presidential Young Investigator Award (1991). She
is a Fellow of the IEEE and a member of the Computing Research Association Board of Directors.
Plenary Talk 2
Session Chair: TBA, Tuesday, July 4, 2023 at 9:00:00 AM CDT – 10:00:00 AM CDT Zurich D
- Invited Talk CEC 2023 (60m)
- Markus Olhofer (Honda Research Institute Europe)
Title: EA based search and AI in engineering applications
Abstract: Evolutionary Computation is well-established in engineering applications. Examples can be found in various search tasks, for example, in the domain of design optimization, which targets finding optimal structures guiding flow of air ventilation systems, aerodynamics of airplanes and cars. Other applications are in the area of energy distribution or scheduling to name a few. Although the focus of the optimization research lies in the identification of optimal solutions for a given problem, it is of equal importance for the engineering task to understand and explain the effects which lead to the performance increase in the system. During the optimization process a large amount of supplementary information is generated in addition to the final result. One important source for such information is given by the path in the design space along which solutions are generated by the evolutionary process. Another source of information is given by detailed simulation results for each single solution generated during the process. However, the latter information is usually far too rich to be processed manually. And finally, the position of the non-dominated solutions on the Pareto-front indicates what is possible to achieve, an important information giving hints especially in early design phases on alternative realizations of a system. To extract and to provide knowledge from all these different types of information is an important step in the application of EA and necessary for an efficient utilization of the results. Once such knowledge is readily available it can in addition be integrated in the search process to improve the evolutionary search. Examples are hyper-parameter tuning and transfer learning but also the definition of suitable representations and operators. In real world applications the optimization process is therefore usually an iterative process including the exploration of the design space, the generation of knowledge and the utilization of knowledge in exploration and decision making. To support this process, it is necessary to combine evolutionary optimization with intelligent methods to generate knowledge about the design space and to interact with the domain experts. In the talk, examples are given from various disciplines which demonstrate the combination of evolutionary optimization methods with AI to form an intelligent system supporting the engineer in generating system knowledge, explore the design space and creating innovative solutions.
Bio: Markus Olhofer
Markus Olhofer is Chief Scientist at the Honda Research Institute Europe since 2010 and responsible for the Complex Systems Optimisation and Analysis Group of the institute. His work currently focuses on the application of evolutionary computation in various engineering domains and on the research on methods to support engineers and designers in the development process. Examples are the optimization of aerodynamic properties for gas turbines and cars, crash worthiness of vehicles or energy management systems. In various research collaborations, special attention was given to the interaction with the designer and the knowledge generation from the process of evolution by learning and statistical data processing in order to support the engineer in an interactive process enhancing the knowledge and the creativity during the process.
Plenary Talk 3
Session Chair: TBD, Wednesday, July 5, 2023 at 9:00:00 AM CDT – 10:00:00 AM CDT Zurich D
- Invited Talk CEC 2023 (60m)
- Kalyanmoy Deb, University Distinguished Professor, Michigan
State University, East Lansing, USA, kdeb@msu.edu
- Kalyanmoy Deb, University Distinguished Professor, Michigan
Title: 30 Years of EMO: Lessons Learned and Tasks Ahead
Abstract of the Lecture: Exactly 30 years ago, the single-objective evolutionary algorithm (EA) framework was successfully extended to solve two-objective optimization problems. That study and a few others came in a quick succession clearly demonstrated that EA’s population approach and ability to find and propagate multiple solutions through generations provided an ideal platform for finding multiple Pareto-optimal solutions in a single run. Since then, a number of systematic studies and events had elevated the simple idea to construct a field of research and application of its own, largely known as “Evolutionary Multi-criterion Optimization” or EMO. The speaker is one of the few who was instrumental right from the beginning and contributed in shaping the field. In this
plenary lecture, speaker’s views on the key advancements that helped built the EMO field will be presented. With a comprehensive and chronological account of past achievements leading to current advancements, the speaker will highlight his views on plausible future
directions for making the EMO research and application more engaging and rewarding.
Bio: Kalyanmoy Deb
Kalyanmoy Deb is University Distinguished Professor and Koenig Endowed Chair Professor at the Department of Electrical and Computer Engineering in Michigan State University. His research interests are in evolutionary optimization and their application in
multi-criterion optimization and machine learning. He was awarded IEEE CIS EC Pioneer award, Infosys Prize, TWAS Prize in Engineering Sciences, CajAstur Mamdani Prize, Distinguished Alumni Award from IIT Kharagpur, Edgeworth-Pareto award, Bhatnagar Prize in Engineering Sciences, and Bessel Research award from Germany. He is fellow of IEEE, ACM, and ASME. He has published over 600 research papers with Google Scholar citation of over 180,000 with h-index 131. More information can be found from: http://www.coin-lab.org