neural networks research group
areas • people • projects • demos • publications • software/data •
SwiftCMA
Released 2019
Download on GitHub

SwiftCMA is a pure-Swift implementation of Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES).

People
Santiago Gonzalez Ph.D. Alumni slgonzalez [at] utexas edu
Publications
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization Santiago Gonzalez and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 305-313, 2021. 2021
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization Santiago Gonzalez and Risto Miikkulainen In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC), 1-8, July 2020. 2020
Areas of Interest
Evolutionary Computation
UT Only: Advice • Calendar • Admin