BriefGPT.xyz
May, 2023
带有引导正则化器的神经网络简化
Neural Network Reduction with Guided Regularizers
HTML
PDF
Ali Haisam Muhammad Rafid, Adrian Sandu
TL;DR
本论文提出了一种名为“引导正则化”的简单新方法，可以在训练过程中优先考虑某些神经网络单元的权重，使得某些单元变得不那么重要而可剪枝，从而实现神经网络的自然简化，在保持性能的同时减少不必要的单元。
Abstract
regularization
techniques such as $\mathcal{L}_1$ and $\mathcal{L}_2$ regularizers are effective in sparsifying
neural networks
(NNs). However, to remove a certain neuron or channel in NNs, all weight elements re
→