Understanding Deep Learning Algorithms that Leverage Unlabeled Data, Part 1: Self-training
We introduce the augmentation graph on the population data, a key concept which allows us to formalize the input consistency regularizer and motivates natural assumptions on the data distribution. In the rest of this blogpost, we’ll
Copy and paste this URL into your WordPress site to embed
Copy and paste this code into your site to embed
Understanding Deep Learning Algorithms that Leverage Unlabeled Data, Part 1: Self-training
We introduce the augmentation graph on the population data, a key concept which allows us to formalize the input consistency regularizer and motivates natural assumptions on the data distribution. In the rest of this blogpost, we’ll