2 papers
cs.LG2020
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization
Santiago Gonzalez, Risto Miikkulainen
Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. Loss functions are a type of metaknowledge that i…
cs.LG2019
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization
Santiago Gonzalez, Risto Miikkulainen
As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning. Methods for discovering hype…