Gavin Gray |
Tue 13 Feb 2018, 11:00 - 12:00 |
IF Room 4.31/4.33 |
If you have a question about this talk, please contact: Gareth Beedham (gbeedham)
Gavin Gray
Moonshine: Distilling with Cheap Convolutions
Joint work with Elliot J. Crowley and Amos Storkey
Model distillation compresses a trained machine learning model, such as a neural network, into a smaller alternative such that it could be easily deployed in a resource limited setting. Unfortunately, this requires engineering two architectures: a student architecture smaller than the first teacher architecture but trained to emulate it. In this paper, we present a distillation strategy that produces a student architecture that is a simple transformation of the teacher architecture. Recent model distillation methods allow us to preserve most of the performance of the trained model after replacing convolutional blocks with a cheap alternative. In addition, distillation by attention transfer provides student network performance that is better than training that student architecture directly on data.