Universidad Autonoma de Madrid, Spain

Bio-inspired Clustering: Basic Features and Future Trends in the Era of Big Data

Abstract: Clustering is perhaps one of the most popular approaches used in unsupervised machine learning. There's a huge number of different methods and algorithms that have been designed in the last decades related to this "blind pattern search", some of these approaches are based on bio-inspired methods such as Evolutionary Computation, Swarm Intelligence or Neural Networks among others. In the last years, and due to the fast growing of Big Data problems, some interesting advances and new approaches are currently being developed in this area, new algorithms like online clustering and streaming clustering are appearing. These new algorithms try to solve classical problems in Clustering and deal with the new features of these new kind of problems. This keynote lecture will provide some basics on both, Clustering methods and bio-inspired computation, and how they have been combined to improve the quality of these algorithms, to later show the main features that Big Data needs to obtain reliable clustering approaches. Finally, some practical examples and applications will be described to show how the new algorithms are evolving to be used in the near future in complex and dynamic environments.

Biographical note: David Camacho is currently working as Associate Professor in the Computer Science Department at Universidad Autónoma de Madrid (Spain) and the Head of the Applied Intelligence & Data Analysis group. He received a Ph.D. in Computer Science (2001) from Universidad Carlos III de Madrid, and a B.S. in Physics (1994) from Universidad Complutense de Madrid. He has published more than 150 journals, books, and conference papers. His research interests includes Data Mining (Clustering), Evolutionary Computation (GA & GP), Multi-Agent Systems and Swarm Intelligence (Ant colonies), Automated Planning and Machine Learning, or Video games among others.