no code implementations • 10 Feb 2020 • Rafael Müller, Simon Kornblith, Geoffrey Hinton
By training a small "student" model to match these probabilities, it is possible to transfer most of the generalization ability of the teacher to the student, often producing a much better small model than directly training the student on the training data.
3 code implementations • NeurIPS 2019 • Rafael Müller, Simon Kornblith, Geoffrey Hinton
The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels.