Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
Sign Up to like & getrecommendations! Published in 2020 at "European Journal of Applied Mathematics"
DOI: 10.1017/s0956792520000406
Abstract: Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning (DL) research. In this paper, we replace the output activation function of… read more here.
Keywords: activation; graph interpolating; data efficient; deep learning ... See more keywords