DeepAI AI Chat
Log In Sign Up

Distilling the Knowledge in a Neural Network

by   Geoffrey Hinton, et al.

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.


page 1

page 2

page 3

page 4


Essence Knowledge Distillation for Speech Recognition

It is well known that a speech recognition system that combines multiple...

Model Agnostic Combination for Ensemble Learning

Ensemble of models is well known to improve single model performance. We...

Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model

Ensembling is a popular method used to improve performance as a last res...

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

Automated Machine Learning (AutoML) frameworks regularly use ensembles. ...

Unfolding and Shrinking Neural Machine Translation Ensembles

Ensembling is a well-known technique in neural machine translation (NMT)...

Quantum Ensemble for Classification

A powerful way to improve performance in machine learning is to construc...

Learning Unified Embedding for Apparel Recognition

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

Code Repositories


Transfer knowledge from a large DNN or an ensemble of DNNs into a small DNN

view repo