no code implementations • 1 Jun 2020 • Andre Mendes, Julian Togelius, Leandro dos Santos Coelho
In this work, we proposed a \textit{Multi-StaGe Transfer Learning} (MSGTL) approach that uses knowledge from simple classifiers trained in early stages to improve the performance of classifiers in the latter stages.
no code implementations • 15 Mar 2020 • Andre Mendes, Julian Togelius, Leandro dos Santos Coelho
We also introduce a sequence constraint in the output of an MLSSL classifier to guarantee the sequential pattern in the predictions.
no code implementations • 15 Mar 2020 • Andre Mendes, Julian Togelius, Leandro dos Santos Coelho
We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains.