Kickstarting Deep Reinforcement Learning proposes a paradigm where 'teacher' agents help train 'student' agents. Benefits include faster research cycles and students that can surpass their teachers: https://arxiv.org/abs/1803.03835
@zacharylipton @furlanel and I have paper on born again networks for supervised learning at meta learning workshop at #nips2017 and we see similar behavior http://metalearning.ml/papers/metalearn17_furlanello.pdf …
-
-
"Born Again Networks" is an interesting read!https://twitter.com/hardmaru/status/941101760017399808 …
"Born Again Neural Networks"
By distilling a teacher model to a student model with an identical architecture, the student outperforms the teacher. They get CIFAR-100 test error down to ~15% using a DenseNet. http://metalearning.ml/papers/metalearn17_furlanello.pdf …Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.