11° Dauin Lunch Seminar - What We Talk About When We Talk About Evolutionary Computation
20 March 2019
Giovanni Squillero (Dauin - Politecnico di Torino)
According to Encyclopedia Britannica, natural evolution is the theory postulating that the various types of plants, animals, and other living things on Earth have their origin in other preexisting types and that the distinguishable differences are due to modifications in successive generations. The elegance of the Darwinian "Natural Selection" fascinated generations of researchers since the end of the XIX century, and inspired different computer scientists in the late 1960s. Their algorithms, loosely inspired by natural evolution, have been successfully used in the past decades for exploring new research lines and solving practical, industrial problems. The fact should not be surprising, as the relationship between learning and evolution has been pointed out by Alan Turing back in 1950 in his seminal work "Computing machinery and intelligence". However, despite its success stories, Evolutionary Computation never experienced a windfall such as Machine Learning today, and these techniques remained almost unnoticed by the general public despite being steadily exploited by practitioners and scholars. The talk will briefly sketch the origin of Evolutionary Computation, what the different research lines have in common and where they differ, and it will highlight the common pitfalls. The current status of the field will be described, along with its potential relationships with modern Machine Leaning (the so-called Evolutionary Machine Learning).
Bio: Giovanni Squillero is an associate professor of computer science at Politecnico di Torino, Department of Control and Computer Engineering. His research mixes the whole spectrum of bio-inspired metaheuristics, computational intelligence, and selected topics from machine learning; in more down-to-earth research lines, he develops approximate optimization techniques able to achieve acceptable solutions with limited amount of resources. Squillero is a Senior Member of the IEEE and serves in the IEEE Computational Intelligence Society Games Technical Committee. He is a member of the editorial board of Genetic Programming and Evolvable Machines and a member of the executive board of SPECIES, the Society for the Promotion of Evolutionary Computation in Europe and its Surroundings. He was the program chair of the European Conference on the Applications of Evolutionary Computation in 2016 and 2017, and he is now a member of the EvoApplications steering committee. In 2018 he co-organized EvoML, the workshop on Evolutionary Machine Learning (PPSN); in 2016 and 2017, MPDEA, the workshop on Measuring and Promoting Diversity in Evolutionary Algorithms (GECCO); and from 2004 to 2014, EvoHOT, the Workshops on Evolutionary Hardware Optimization Techniques (EvoSTAR).
- Darwin, C., On The Origin of Species by Means of Natural Selection, or Preservation of Favoured Races in the Struggle for Life. London: John Murray, 1859.
- Turing, A. M., Computing Machinery and Intelligence. Mind, LIX, 236. p. 433-460. Oxford University Press, 1950.
- Holland, J. Henry and others, Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press, 1992.
- Eiben A.E. and Smith E.J., Introduction to Evolutionary Computing. Springer Berlin Heidelberg, 2015.
- Jay Gould, S., The structure if evolutionary theory, Harvard University Press, 2002.
Registration on https://dauin_lunch11.eventbrite.com.