Introduction to Active Learning

Abhimanyu Aryan | August 26, 2019 · 1 min read

Edit on GithubEdit on Github

Active learning was introduced by burr settles at University of Wisconsin

According to Wikipedia, Active Learning is sub-field in Semi Supervised Learning. Let’s understand Semi Supervised Learning in layman terms:

the ability to get a large number of images makes this a great candidate for semi supervised learning

a very simple approach of semi supervised learning…

  • capture 11,000 images
  • label 100 images & train model_1
  • use model_1 to label other 10900 images
  • train model_2 with "labelled" 10,000
... results in a model_2 that does better than model_1.

Written by

Abhimanyu Aryan

Hi, I'm Abhimanyu Aryan, Deep Learning practitioner. Click here if you want know more about me or checkout my portfolio.