Skip to yearly menu bar Skip to main content


Poster

Automated Curriculum Learning for Neural Networks

Alex Graves · Marc Bellemare · Jacob Menick · Remi Munos · Koray Kavukcuoglu

Gallery #127

Abstract:

We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the amount that the network learns from each data sample is provided as a reward signal to a nonstationary multi-armed bandit algorithm, which then determines a stochastic syllabus. We consider a range of signals derived from two distinct indicators of learning progress: rate of increase in prediction accuracy, and rate of increase in network complexity. Experimental results for LSTM networks on three curricula demonstrate that our approach can significantly accelerate learning, in some cases halving the time required to attain a satisfactory performance level.

Live content is unavailable. Log in and register to view live content