BriefGPT.xyz
May, 2017
需要糟糕的GAN的有效半监督学习
Good Semi-supervised Learning that Requires a Bad GAN
HTML
PDF
Zihang Dai, Zhilin Yang, Fan Yang, William W. Cohen, Ruslan Salakhutdinov
TL;DR
本文讨论基于生成对抗网络（GANs）的半监督学习方法，研究表明在鉴别器的目标下，需要一个差劣的生成器，提出了首选生成器的定义，并在多个基准数据集上显著改善了特征匹配GANs，取得了最新的结果。
Abstract
semi-supervised learning
methods based on
generative adversarial networks
(GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and
→