Compressing deep learning models: distillation (Ep.104)
May 20, 2020•22 min•Ep. 101
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
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
For the best experience, listen in Metacast app for iOS or Android