Sara Silva (INESC-ID)
A Tutorial on Genetic Programming
Genetic Programming (GP) is the youngest paradigm inside the Artificial Intelligence field called Evolutionary Computation. Created by John Koza in 1992, it can be regarded as a powerful generalization of Genetic Algorithms, but unfortunately it is still poorly understood outside the GP community. The goal of this tutorial is to provide motivation, intuition and practical advice about GP, along with very few technical details.
Bio: Sara Silva is a senior researcher of the Knowledge Discovery and Bioinformatics (KDBIO) group at INESC-ID Lisboa, Portugal, and an invited researcher of the Evolutionary and Complex Systems (ECOS) group at CISUC, Portugal. She has a BSc and a MSc in Informatics by the Faculty of Sciences of the University of Lisbon, and a PhD in Informatics Engineering by the Faculty of Sciences and Technology of the University of Coimbra. After graduation she used neural networks and genetic algorithms in several interdisciplinary projects ranging from remote sensing and forest science to epidemiology and medical informatics. She started her research on GP in 2002, studying the bloat problem. Her main contributions to this field were the Dynamic Limits and Resource-Limited GP bloat control methods, and the developments that put into practice the new Operator Equalisation method. Her current main research interests are bloat and overfitting in GP, and how they relate to each other, and the effective and efficient usage of GP in real life problems within the earth sciences and bioinformatics domains. She is a member of the editorial board of Genetic Programming and Evolvable Machines, and the creator of GPLAB - A Genetic Programming Toolbox for MATLAB.