Santiago Gonzalez

Research

Santiago Gonzalez was a PhD student at the University of Texas at Austin where he was part of the Neural Networks Research Group, working with Dr. Risto Miikkulainen, with research focussing on neuroevolution and metalearning.

While pursuing his MS in Computer Science from the Colorado School of Mines, Gonzalez was working with Dr. Tracy Camp. As part of his thesis research, he developed a lightweight time synchronization protocol for wireless sensor networks.

Publications

• Santiago Gonzalez and Risto Miikkulainen (2021)
  Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization
  In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '21).
• Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, and Risto Miikkulainen (2021)
  Regularized Evolutionary Population-Based Training
  In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '21).
• Santiago Gonzalez and Risto Miikkulainen (2021)
  Evolving GAN Formulations for Higher Quality Image Synthesis
  arXiv:2102.08578.
• Santiago Gonzalez and Risto Miikkulainen (2021)
  Effective Regularization Through Loss-Function Metalearning
  arXiv:2010.00788.
• Olivier Francon, Santiago Gonzalez, Babak Hodjat, Elliot Meyerson, Risto Miikkulainen, Xin Qiu, and Hormoz Shahrzad (2020)
  Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
  In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '20).
  Best-Paper Award in the GECH track.
• Santiago Gonzalez and Risto Miikkulainen (2020)
  Improved Training Speed, Accuracy, and Data Utilization Through Loss-Function Optimization
  In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '20).
• Santiago Gonzalez, Joshua Landgraf, and Risto Miikkulainen (2019)
  Faster Training by Selecting Samples Using Embeddings
  In Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN '19), Budapest, Hungary, July, 2019.
• Santiago Gonzalez, Vijay Chidambaram, Jivko Sinapov, and Peter Stone (2017)
  CC-Log: Drastically Reducing Storage Requirements for Robots Using Classification and Compression
  In Proceedings of the 9th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage '17), Santa Clara, CA, July 10-11, 2017.
• Santiago Gonzalez, Tracy Camp, and Katia Jaffrès-Runser (2017)
  The Sticking Heartbeat Aperture Resynchronization Protocol
  In Proceedings of the 26th International Conference on Computer Communication and Networks (ICCCN), Vancouver, BC, Canada, 2017.
• Santiago Gonzalez (2015)
  Improving Time Synchronization Protocols in Wireless Sensor Networks
  Masters Thesis, Colorado School of Mines, December 2015.
• Tracy Camp, Marc J. Rubin, and Santiago Gonzalez (2015)
  Challenges in developing intelligent geosystems (and the pros/cons of interdisciplinary research)
  In Proceedings of the 2015 International Conference on Computing, Networking and Communications (ICNC).