BriefGPT.xyz
Oct, 2017
通过噪声使深度神经网络规则化：解释和优化
Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
HTML
PDF
Hyeonwoo Noh, Tackgeun You, Jonghwan Mun, Bohyung Han
TL;DR
通过多次噪声注入来提高泛化性能使得深度神经网络可以更好地防止过拟合，本文提出了一种使用随机梯度下降迭代中每个训练样本的多个噪声样本来实现更紧密下界的技术，并在几个计算机视觉应用中展示了其优越性。
Abstract
overfitting
is one of the most critical challenges in deep neural networks, and there are various types of
regularization
methods to improve generalization performance. Injecting noises to hidden units during tra
→