Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, Yee Whye Teh
TL;DR深度神经网络修剪方法的全面理论分析及其在各种网络架构上的实验验证。
Abstract
overparameterized neural networks display state-of-the art performance. However, there is a growing need for smaller, energy-efficient, neural networks to be able to use machine learning applications on devices with limited computational resources. A popular approach consists of using