papers AI Learner
The Github is limit! Click to go to the new site.

Deep Active Learning with a Neural Architecture Search

2018-11-19
Yonatan Geifman, Ran El-Yaniv

Abstract

We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby the learning algorithm searches for effective architectures on the fly, while actively learning. We apply our strategy using three known querying techniques (softmax response, MC-dropout, and coresets) and show that the proposed approach overwhelmingly outperforms active learning using fixed architectures.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.07579

PDF

https://arxiv.org/pdf/1811.07579


Similar Posts

Comments