One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectr...| papers.cool
We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to perturbation, we propose a simple and effective regularization method, referred to as spectral norm regularization, which penalizes the high spectral norm of weight matrices in neural networks. We provide supportive evidence for the abovementioned hypothesis by expe...| papers.cool
前言GAN，全称Generative Adversarial Nets，中文名是生成对抗式网络。对于GAN来说，最通俗的解释就是“伪造者-鉴别者”的解释，如艺术画的伪造者和鉴别者。一开始伪造者和...| kexue.fm
Eigenvalue algorithm| en.wikipedia.org
前言：去年写过一篇WGAN-GP的入门读物《互怼的艺术：从零直达WGAN-GP》，提到通过梯度惩罚来为WGAN的判别器增加Lipschitz约束（下面简称“L约束”）。前几天遐想时再次想到了WG...| kexue.fm
事实上，除了写博客内容，在这几年里，笔者是花了相当一部分时间来做科学空间的“表面功夫”，为此还专门学了一点php、css和js。虽然不敢说精益求精，但总体来说网站的浏览体验应该比前几年要好得多。...| kexue.fm