Modern Deep Learning Design and Application Development: Versatile Tools to Solve Deep Learning Problems

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022

A. YeModern Deep Learning Design and Application Developmenthttps://doi.org/10.1007/978-1-4842-7413-2_4

4. Model Compression for Practical Deployment

Andre Ye¹  

(1)

Redmond, WA, USA

 

It is my ambition to say in 10 sentences what everyone else says in a book.

—Friedrich Nietzsche, Philosopher and Writer¹

Over the course of deep learning’s flurried development in these recent decades, model compression has relatively recently become of prominent importance. Make no mistake – model compression methods have existed and have been documented for decades, but the focus for much of deep learning’s recent evolution was on expanding and increasing the size of deep learning ...