AI summary

This paper introduces a distillation technique to compress the knowledge of an ensemble of models into a single model. It achieves strong results on MNIST and significantly improves the acoustic model of a commercial system, and introduces a new type of ensemble composed of full and specialist models.

Abstract

A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions [3]. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow de- ployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators [1] have shown that it is possible to compress the knowledge in an ensemble into a single model which is much eas- ier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full mod- els confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.