Santiago Gonzalez
Ph.D. Alumni
Santiago Gonzalez was a PhD student interested in the intersection of evolution and metalearning who graduated from UT Austin in December 2020. Before coming to UT Austin, Gonzalez got a BS and an MS in Computer Science from the Colorado School of Mines.
Homepage:
slgonzalez.com
Effective Regularization Through Loss-Function Metalearning 2021
Santiago Gonzalez and Risto Miikkulainen, arXiv:2010.00788 (2021).
Evolving GAN Formulations for Higher Quality Image Synthesis 2021
Santiago Gonzalez, Mohak Kant, and Risto Miikkulainen, arXiv:2102.08578 (2021).
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization 2021
Santiago Gonzalez and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, 2021.
Regularized Evolutionary Population-Based Training 2021
Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, 2021.
Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription 2020
Olivier Francon, Santiago Gonzalez, Babak Hodjat, Elliot Meyerson, Risto Miikkulainen, Xin Qiu, Hormoz Shahrzad, In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2020), 2020.
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization 2020
Santiago Gonzalez and Risto Miikkulainen, In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC), July 2020.
Improving Deep Learning Through Loss-Function Evolution 2020
Santiago Gonzalez, PhD Thesis, Department of Computer Science, The University of Texas at Austin.
Faster Training by Selecting Samples Using Embeddings 2019
Santiago Gonzalez, Joshua Landgraf, and Risto Miikkulainen, Proceedings of the 2019 International Joint Conference on Neural Networks (2019).
SwiftCMA Download on GitHub

SwiftCMA is a pure-Swift implementati...
2019

SwiftGenetics Download on GitHub

SwiftGenetics is a genetic algor...
2019

Formerly affiliated with Neural Networks