Dr. Faustino Gomez
Faustino Gomez, Ph.D. is
Senior Researcher at the
Dalle Molle Institute for Artificial Intelligence.
His research focuses on using artificial evolution to automatically design neural network solutions to reinforcement learning tasks. This general approach can potentially provide a way to solve complex real-world control problems in areas such as aerospace and autonomous robotics where it is often too difficult to design effective controllers by conventional engineering methods.
In addition to developing algorithms that can solve such tasks, Faustino is also interested in studying techniques for making evolved controllers robust so that they can successfully make the transition from simulation to the real world, and therefore actually be useful in industry.
Faustino authored Sustaining Diversity using Behavioral Information Distance, and coauthored Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices, Evolving Neural Networks in Compressed Weight Space, Measuring and Optimizing Behavioral Complexity, Countering Poisonous Inputs with Memetic Neuroevolution, Evolino for Recurrent Support Vector Machines, and Co-Evolving Recurrent Neurons Learn Deep Memory POMDPs. Read the full list of his publications!
Faustino earned his BA in Geography at Clark University, Worcester, Massachusetts in 1991 and his Ph.D. in Computer Science at the University of Texas at Austin in 2003 with the thesis Robust Non-Linear Control through Neuroevolution.