Distilling the Knowledge in a Neural Network

03/09/2015
by   Geoffrey Hinton, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2019

Essence Knowledge Distillation for Speech Recognition

It is well known that a speech recognition system that combines multiple...
research
06/16/2020

Model Agnostic Combination for Ensemble Learning

Ensemble of models is well known to improve single model performance. We...
research
05/24/2022

Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model

Ensembling is a popular method used to improve performance as a last res...
research
07/01/2023

Assembled-OpenML: Creating Efficient Benchmarks for Ensembles in AutoML with OpenML

Automated Machine Learning (AutoML) frameworks regularly use ensembles. ...
research
04/11/2017

Unfolding and Shrinking Neural Machine Translation Ensembles

Ensembling is a well-known technique in neural machine translation (NMT)...
research
07/02/2020

Quantum Ensemble for Classification

A powerful way to improve performance in machine learning is to construc...
research
07/19/2017

Learning Unified Embedding for Apparel Recognition

In apparel recognition, specialized models (e.g. models trained for a pa...

Please sign up or login with your details

Forgot password? Click here to reset