Automated Curriculum Learning for Neural Networks
ICML, pp. 1311-1320, 2017.
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 sto...More
PPT (Upload PPT)