MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted LabelsEI
ICML, pp. 2309-2318, 2018.
Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet, to supervise the training of the base deep networks, namely, StudentNet. During training, MentorNet p...More