资源分类
》 资源 》论文》Deep Active Learning with a Neural Architecture Search

Deep Active Learning with a Neural Architecture Search

2020-02-23 | |  32 |   32 |   0

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.

上一篇：Elliptical Perturbations for Differential Privacy

下一篇：PHYRE: A New Benchmark for Physical Reasoning

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to learn...

    The move from hand-designed features to learned...