Perspectives on Evolutionary Computing: Achievements and Challenges
SICSA Distinguished Visitor: Professor Enrique Alba, University of Málaga, Spain
Among the many modern and effective techniques for search, optimization, and machine learning, Evolutionary Computing represents a family of exceptionally important algorithms whose natural inspiration has led them to solve open problems in science and industry.
After their initial proposal, many years of development produced genetic algorithms, evolution strategies, genetic programming and many new types of evolutionary algorithms that were first seen as black boxes ready to allow researchers solve with accuracy their problems in virtually every domain of knowledge: medicine, logistics, software, telecoms, and a long etcetera.
Soon after, theory and computational extensions came, digging into their nature and the way of solving real problems. Thus, hybrids, ensembles, new operators, new representations, and new search landscape analyses appeared, to transform them not only into precise but also into efficient techniques well beyond the early results needing considerable computation times.
Nowadays, evolutionary algorithms represent a healthy and large field of research, development and innovation in actual companies. They are reaching our cities (reduction of pollution, smart mobility, circular economy…), our agriculture (watering intelligent systems), our skies (drone management), and our seas (energy, conservation, unmanned vehicles…).
This talk will present several past achievements, new challenges, and some latest advances such as dynamic resolution of problems, distributed techniques, many-objective optimization, neuro-evolution, edge computing, and quantum optimization, to name a few.
Prof. Enrique Alba had his degree in engineering and PhD in Computer Science in 1992 and 1999, respectively, by the University of Málaga (Spain). He works as a Full Professor in this university with varied teaching duties: data communications, distributed programming, software quality, and also evolutionary algorithms, bases for R+D+i and smart cities, both at graduate and master/doctoral programs.