Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks

Understand

Curriculum Learning emphasizes the order of training instances in a computational learning setup.

• The core hypothesis is that simpler instances should be learned early as building blocks to learn more complex ones.
• Despite its usefulness, it is still unknown how exactly the internal representation of models are affected by curriculum learning.
• In this paper, we study the effect of curriculum learning on Long Short-Term Memory (LSTM) networks, which have shown strong competency in many Natural Language Processing (NLP) problems.