BriefGPT.xyz
Nov, 2020
基于损失的敏感性正则化：面向深度稀疏神经网络
LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks
HTML
PDF
Enzo Tartaglione, Andrea Bragagnolo, Attilio Fiandrotti, Marco Grangetto
TL;DR
LOBSTER 是一种用于训练稀疏拓扑的神经网络的方法，通过减少灵敏性最小化对损失函数的影响，从而稀疏化网络。在多个体系结构和数据集上进行的实验显示出具有竞争性的压缩比和最小的计算负担。
Abstract
lobster
(LOss-Based SensiTivity rEgulaRization) is a method for training
neural networks
having a
sparse topology
. Let the sensitivity of
→