Compressing deep learning models: distillation (Ep.104)

05/20/20 • 22 min

Using large deep learning models on limited hardware or edge devices is definitely prohibitive. There are methods to compress large models by orders of magnitude and maintain similar accuracy during inference.

In this episode I explain one of the first methods: knowledge distillation

Come join us on Slack

Reference

Distilling the Knowledge in a Neural Network https://arxiv.org/abs/1503.02531
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks https://arxiv.org/abs/2004.05937

In this episode I explain one of the first methods: knowledge distillation

Come join us on Slack

Reference

Distilling the Knowledge in a Neural Network https://arxiv.org/abs/1503.02531
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks https://arxiv.org/abs/2004.05937

Previous Episode

Pandemics and the risks of collecting data (Ep. 103)

Codiv-19 is an emergency. True. Let's just not prepare for another emergency about privacy violation when this one is over.

Join our new Slack channel

This episode is supported by Proton. You can check them out at protonmail.com or protonvpn.com

Next Episode

Compressing deep learning models: rewinding (Ep.105)

As a continuation of the previous episode in this one I cover the topic about compressing deep learning models and explain another simple yet fantastic approach that can lead to much smaller models that still perform as good as the original one.

Don't forget to join our Slack channel and discuss previous episodes or propose new ones.

This episode is supported by Pryml.io
Pryml is an enterprise-scale platform to synthesise data and deploy applications built on that data back to a production environment.

References

Comparing Rewinding and Fine-tuning in Neural Network Pruning
https://arxiv.org/abs/2003.02389