Dr. Faustino Gomez

CEO at NNAISENSE

• Senior Researcher working with Juergen Schmidhuber, 2004-2014.
• PhD Computer Science, University of Texas at Austin, 2003.
• BA Geography, Clark University, Worcester, MA, 1991.

Research Description

My research has focused 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, I am 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.

Publications

• Rupesh Kumar Srivastava, Jonathan Masci, Faustino Gomez, and Juergen Schmidhuber (2015). Understanding Locally Competitive Networks. In Proceedings of Internatinoal Conference on Learning Representations (ICLR).
• Marijn Stollenga, Jonathan Masci, Faustino Gomez, and Juergen Schmidhuber (2014). Deep Networks with Internal Selective Attention through Feedback Connections. In Proceedings of Neural Information Processing Systems (NIPS).
• Jan Koutnik, Juergen Schmidhuber, and Faustino Gomez (2014). Online Evolution of Deep Convolutional Networks for Reinforcement Learning. In Proceedings of the Simulation of Adaptive Behavior Conference (SAB, Castellon, ES).
• Marijn Stollenga, Juergen Schmidhuber, and Faustino Gomez (2014). Rapid Humanoid Motion Learning through Coordinated, Parallel Evolution. In Proceedings of the Simulation of Adaptive Behavior Conference (SAB, Castellon, ES).
• Jan Koutnik, Juergen Schmidhuber, and Faustino Gomez (2014). Evolving Deep Unsupervised Convolutional Networks for Vision-Based Reinforcement Learning. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO, Vancouver, CA).
• Jan Koutnik, Klaus Greff, Faustino Gomez, Juergen Schmidhuber (2014). A Clockwork RNN. In Proceedings of the International Conference on Machine Learning (ICML, Beijing).
• Rupesh Kumar Srivastava, Jonathan Masci, Sohrob Kazerounian, Faustino Gomez, and Juergen Schmidhuber (2013). Compete to Compute. In Proceedings of Neural Information Processing Systems (NIPS, Lake Tahoe).
• Jan Koutnik, Giuseppe Cuccu, Juergen Schmidhuber, and Faustino Gomez (2013). Evolving Large-Scale Neural Networks for Vision-Based TORCS. In Foundations of Digital Games (FDG, Chania, Crete).
• Yi Sun, Faustino Gomez, Tom Schaul, and Juergen Schmidhuber (2013). A Linear Time Natural Evolution Strategy for Non-Separable Functions. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO, Amsterdam), arXiv:1106.1998v2 (2011).
• Jan Koutnik, Giuseppe Cuccu, Juergen Schmidhuber, and Faustino Gomez (2013). Evolving Large-Scale Neural Networks for Vision-Based Reinforcement Learning. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO, Amsterdam).
• Jan Koutnik, Juergen Schmidhuber, and Faustino Gomez (2012). A Frequency-Domain Encoding for Neuroevolution. arxiv.org/abs/1212.6521
• Faustino Gomez, Jan Koutnik, and Juergen Schmidhuber (2012). Compressed Network Complexity Search. In Proceedings of the 12th International Conference on Parallel Problem Solving from Nature (PPSN XII, Taormina, IT).
• Rupesh Kumar Srivastava, Juergen Schmidhuber, and Faustino Gomez (2012). Generalized Compressed Network Search. In Proceedings of the 12th International Conference on Parallel Problem Solving from Nature (PPSN XII, Taormina, IT).
• Giuseppe Cuccu and Faustino Gomez (2012). Block Diagonal Natural Evolution Strategies. In Proceedings of the 12th International Conference on Parallel Problem Solving from Nature (PPSN XII, Taormina, IT).
• Yi Sun, Faustino Gomez, and Juergen Schmidhuber (2012). On the Size of the Online Kernel Sparsification Dictionary. In Proceedings of the International Conference on Machine Learning (ICML, Edinburgh).
• Rupesh Kumar Srivastava, Juergen Schmidhuber, Faustino Gomez (2012). Generalized Compressed Network Search. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-12, Philadelphia).
• Faustino Gomez, Jan Koutnik, and Juergen Schmidhuber (2012). Complexity Search for Compressed Neural Networks. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-12, Philadelphia).
• Giuseppe Cuccu, Matthew Luciw, Juergen Schmidhuber, and Faustino Gomez (2011). Intrinsically Motivated NeuroEvolution for Vision-Based Reinforcement Learning. In Proceedings of the International Conference on Development and Learning (ICDL, Frankfurt).
• Yi Sun, Faustino Gomez, and Juergen Schmidhuber (2011). Planning to be Surprised: Optimal Bayesian Exploration in Dynamic Environments. In Proceedings of the Artificial General Intelligence Conference (AGI, Mountainview, CA).
• Yi Sun, Faustino Gomez, Mark Ring, and Juergen Schmidhuber (2011). Incremental Basis Construction from Temporal Difference Error. In Proceedings of the International Conference on Machine Learning (ICML, Bellevue, WA).
• Leo Pape, Faustino Gomez, Mark Ring, and Juergen Schmidhuber (2011). Modular Deep Belief Networks that do not Forget. In Proceedings of the International Joint Conference on Neural Networks (IJCNN, San Jose, CA).
• Tom Schaul, Yi Sun, Daan Wierstra, Faustino Gomez, and Juergen Schmidhuber (2011). Curiosity-Driven Optimization. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC, New Orleans).
• Giuseppe Cuccu, Faustino Gomez, and Tobias Glasmachers (2011). Novelty-Based Restarts for Evolutionary Strategies. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC, New Orleans).
• Giuseppe Cuccu and Faustino Gomez (2011). When Novelty is Not Enough. In Proceedings of Evostar 2011 (Turin, Italy).
• Yi Sun, Faustino Gomez, and Juergen Schmidhuber (2010). Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices. In Advances in Neural Information Processing Systems (NIPS).
• Jan Koutnik, Faustino Gomez, and Juergen Schmidhuber (2010). Evolving Neural Networks in Compressed Weight Space. In Proceedings of the Conference on Genetic and Evolutionary Computation (GECCO-10), pp 619-626.
• Jan Koutnik, Faustino Gomez, and Juergen Schmidhuber (2010). Searching for Minimal Neural Networks in Fourier Space. In Proceedings of the Third Conference on Artificial General Intelligence (AGI-10, Lugano, Switzerland), pp 61-66.
• Faustino Gomez, Julian Togelius, and Juergen Schmidhuber (2009). Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning. In Proceedings of the International Conference on Artificial Neural Networks (ICANN-09, Lamissol, Cyprus), pp 765-774.
• Julian Togelius, Tom Schaul, Daan Wierstra, Christian Igel, Faustino Gomez, and Juergen Schmidhuber (2009). Ontogenetic and Phylogenetic Reinforcement Learning. Kuenstliche Intelligenz
• Faustino Gomez (2009). Sustaining Diversity using Behavioral Information Distance. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-09, Montreal), pp 113-120. Nominated for Best Paper in Artificial Life, Evolutionary Robotics, Adaptive Behavior, and Evolvable Hardware.
• Julian Togelius, Tom Schaul, Juergen Schmidhuber, and Faustino Gomez (2008). Countering Poisonous Inputs with Memetic Neuroevolution. In Proceedings of the International Conference on Parallel Problem Solving From Nature (PPSN-08, Dortmund).
• Hermann Mayer, Faustino Gomez, Daan Wierstra, Istvan Nagy, Alois Knoll, and Juergen Schmidhuber (2008). A System for Robotic Heart Surgery that Learns to Tie Knots using Recurrent Neural Networks. Advanced Robotics, 22(13-14), pp 1521-1537.
• Faustino Gomez, Juergen Schmidhuber and Risto Miikkulainen (2008). Accelerated Neural Evolution through Cooperatively Coevolved Synapses. Journal of Machine Learning Research 9(May), pp 937-965.
• Julian Togelius, Faustino Gomez, and Juergen Schmidhuber (2008). Learning What to Ignore: Memetic Climbing in Topology an Weight Space. In Proceedings of the Congress on Evolutionary Computation (CEC-08, Hong Kong).
• Juergen Schmidhuber, Daan Wierstra, Matteo Gagliolo, and Faustino Gomez (2007). Training Recurrent Neural Networks by Evolino. Neural Computation 19(3), pp 757-779.
• Faustino Gomez, Juergen Schmidhuber, and Risto Miikkulainen (2006). Efficient Non-Linear Control through Neuroevolution. In Proceedings of the European Conference on Machine Learning (ECML-06, Berlin).
• Hermann Mayer, Faustino Gomez, Daan Wierstra, Istvan Nagy, Alois Knoll, and Juergen Schmidhuber (2006). A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks. In Proceedings of the International Conference on Intelligent Robotics and Systems (IROS-06, Beijing). Best Paper Finalist.
• Alex Graves, Santiago Fernandez, Faustino Gomez, and Juergen Schmidhuber (2006). Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. In Proceedings of the International Conference on Machine Learning (ICML-06, Pittsburgh).
• Juergen Schmidhuber, Matteo Gagliolo, Daan Wierstra, and Faustino Gomez (2006). Evolino for Recurrent Support Vector Machines. In Proceedings of the European Symposium on Artificial Neural Networks (ESANN-06, Bruge).
• Viktor Zhumatiy, Faustino Gomez, Marcus Hutter, and Juergen Schmidhuber (2006). Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot. In Proceedings of the International Conference on Intelligent Autonomous Systems (IAS-06, Tokyo).
• Faustino Gomez and Juergen Schmidhuber (2005). Evolving Modular Fast-Weight Networks for Control. In Proceedings of the International Conference on Artificial Neural Networks (ICANN-05, Warsaw).
• Faustino Gomez and Juergen Schmidhuber (2005). Co-Evolving Recurrent Neurons Learn Deep Memory POMDPs. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-05, Washington, D.C.). Nominated for Best Paper in Coevolution.
• Daan Wierstra, Faustino Gomez, and Juergen Schmidhuber (2005). Modeling Systems with Internal State using Evolino. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-05, Washington, D.C.). Winner of Best Paper Award in Learning Classifier Systems and Other Genetics-Based Machine Learning.
• Juergen Schmidhuber, Daan Wierstra, and Faustino Gomez (2005). Evolino: Hybrid Neuroevolution / Optimal Linear Search for Sequence Learning. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-05, Edinburgh).
• Faustino Gomez and Risto Miikkulainen (2004). Transfer of Neuroevolved Controllers in Unstable Domains. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-04, Seattle).
• Faustino Gomez and Risto Miikkulainen (2003). Active Guidance for a Finless Rocket through Neuroevolution. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-03, Chicago). Winner of Best Paper Award in Real World Applications (DEMO VIDEO).
• Faustino Gomez and Risto Miikkulainen (2001). Dynamic Resource Allocation for a Chip-Multiprocessor using Neuroevolution. In Proceedings of the International Joint Conference on Neural Networks (IJCNN-01, Washington, D.C.)
• Faustino Gomez and Risto Miikkulainen (1999). Solving Non-Markovian Control Tasks with Neuroevolution. In Proceedings of the International Joint Conference on Artificial Intellignce (IJCAI-99, Stockholm, Sweden), Denver: Morgan Kaufmann. (DEMO VIDEO).
• Faustino Gomez and Risto Miikkulainen (1998). 2-D Pole Balancing with Recurrent Evolutionary Networks. In Proceedings of the International Conference on Artificial Neural Networks (ICANN-98, Skovde, Sweden), 425-430. Berlin, New York: Springer.
• Faustino Gomez and Risto Miikkulainen (1997). Incremental Evolution of Complex General Behavior Adaptive Behavior, 5:317-342.
• Faustino Gomez and Risto Miikkulainen (1996). Evolving Complex General Behavior in Stochastic, Dynamic Environments, Working Notes of the AAAI Fall Symposium on Learning Complex Behaviors in Adaptive Intelligent Systems, 140-147, AAAI.

PhD Thesis

• Faustino Gomez (2003). Robust Non-Linear Control through Neuroevolution, Department of Computer Sciences Technical Report AI-TR-03-303, August 2003.

Tech Reports

• Faustino Gomez and Risto Miikkulainen (2002). Robust Non-Linear Control through Neuroevolution, Department of Computer Sciences Technical Report AI-TR-02-292, October 2002.

EU Research Projects