upcarta
  • Sign In
  • Sign Up
  • Explore
  • Search

Human in the Loop: Deep Learning without Wasteful Labelling

  • Article
  • 2019
  • #ArtificialIntelligence #MachineLearning
Andreas Kirsch
@BlackHC
(Author)
Yarin Gal
@yaringal
(Author)
Joost van Amersfoort
@joost_v_amersf
(Author)
oatml.cs.ox.ac.uk
Read on oatml.cs.ox.ac.uk
1 Recommender
1 Mention
Using deep learning and a large labelled dataset, we are able to obtain excellent performance on a range of important tasks. Often, however, we only have access to a large unlabelle... Show More

Using deep learning and a large labelled dataset, we are able to obtain excellent performance on a range of important tasks. Often, however, we only have access to a large unlabelled dataset. For example, it is easy to acquire lots of stock photos, but labelling these images is time-consuming and expensive. This excludes many applications from benefiting from recent advances in deep learning.

In Active Learning we only ask experts to label the most informative data points instead of labelling the whole dataset upfront. The model is then retrained using these newly acquired data points and all previously labelled data points. This process is repeated until we are happy with the accuracy of our model.

To perform Active Learning, we need to define some measure of informativeness, which is often done in the form of an acquisition function. This measure is called an “acquisition function” because the score it computes determines which data points we want to acquire. We send unlabelled data points which maximise the acquisition function to an expert and ask for labels.

Show Less
Recommend
Post
Save
Complete
Collect
Mentions
See All
Clare Lyle @clarelyle · Jun 25, 2019
  • Post
  • From Twitter
highly recommend reading this blog post for both the science and the stunning aesthetics 😍. Well done @BlackHC @joost_v_amersf !
  • upcarta ©2025
  • Home
  • About
  • Terms
  • Privacy
  • Cookies
  • @upcarta