13

[1503.02531] Distilling the Knowledge in a Neural Network

 3 years ago
source link: https://arxiv.org/abs/1503.02531
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

[Submitted on 9 Mar 2015]

Distilling the Knowledge in a Neural Network

Download PDF

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. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier 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 models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.

Comments: NIPS 2014 Deep Learning Workshop Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:1503.02531 [stat.ML]   (or arXiv:1503.02531v1 [stat.ML] for this version)   https://doi.org/10.48550/arXiv.1503.02531

report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK