Faustino Gomez
Postdoctoral Alumni, Ph.D. Alumni
In his dissertation work, Tino developed the Enforced SubPopulations (ESP) neuroevolution method and applied it to robust nonlinear control, including that of a finless rocket RSX-2. He went on to work at IDSIA, Switzerland, where he extended the method further into the level of individual weights in CoSYNE, and has applied it to several domains in robotics and otherwise. He is also passionate about designing and building guitars.
Homepage:
http://www.idsia.ch/~tino/
Publications
Accelerated Neural Evolution through Cooperatively Coevolved Synapses 2008
Faustino Gomez, Juergen Schmidhuber, and Risto Miikkulainen, Journal of Machine Learning Research (2008), pp. 937-965.
Efficient Non-Linear Control through Neuroevolution 2006
Faustino Gomez, Juergen Schmidhuber, and Risto Miikkulainen, In Proceedings of the European Conference on Machine Learning, pp. 654-662, Berlin 2006. Springer.
Transfer of Neuroevolved Controllers in Unstable Domains 2004
Faustino J. Gomez and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, Berlin 2004. Springer.
Active Guidance for a Finless Rocket Using Neuroevolution 2003
Faustino J. Gomez and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 2084-2095, San Francisco 2003. Morgan Kaufmann.
PhD Thesis: Robust Non-Linear Control through Neuroevolution 2003
Faustino J. Gomez, Technical Report AI-TR-03-303, Department of Computer Sciences, University of Texas at Austin.
Robust Non-Linear Control through Neuroevolution 2003
Faustino J. Gomez, PhD Thesis, Department of Computer Sciences, The University of Texas at Austin.
A Neuroevolution Method For Dynamic Resource Allocation On A Chip Multiprocessor 2001
Faustino J. Gomez, Doug Burger, and Risto Miikkulainen, In Proceedings of the {INNS-IEEE} International Joint Conference on Neural Networks, pp. 2355-2361, Piscataway, NJ 2001. IEEE.
Solving Non-Markovian Control Tasks With Neuroevolution 1999
Faustino J. Gomez and Risto Miikkulainen, In Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1356-1361, San Francisco, CA 1999. Kaufmann.
2-D Pole Balancing With Recurrent Evolutionary Networks 1998
Faustino Gomez and Risto Miikkulainen, In Proceedings of the International Conference on Artificial Neural Networks (ICANN-98), pp. 425-430, Skovde, Sweden 1998. Berlin, New York: Springer.
Incremental Evolution Of Complex General Behavior 1997
Faustino Gomez and Risto Miikkulainen, Adaptive Behavior, 5 (1997), pp. 317-342.
Projects
Controlling a Finless Rocket Through Neuroevolution 2002 - 2003
Dynamic Resource Allocation on a Multiprocessor Chip 2000 - 2002
Solving Non-Markov Control Tasks 1996 - 2006
Areas of Interest
Control Evolutionary Computation Neuroevolution Robotics
Software/Data
CoSyNE C++ CoSyNE is a neuroevolution method where synapses of the network are evolved in separate subpopulations in a cooperative ... 2011
ESP C++ The ESP package contains the source code for the Enforced Sup-Populations system written in C++. ESP is an extension t... 2000
Demos
Finless Rocket ControlFaustino Gomez2003
Double Pole Balancing with ESPFaustino Gomez1999
Labs
Formerly affiliated with Neural Networks