BriefGPT.xyz
Jun, 2016
f-GAN: 使用变分差异最小化训练生成性神经采样器
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
HTML
PDF
Sebastian Nowozin, Botond Cseke, Ryota Tomioka
TL;DR
本文研究了生成性神经采样器的概率模型及训练方法，探讨了各类分歧函数的使用对训练效率和生成模型的影响。
Abstract
generative neural samplers
are
probabilistic models
that implement sampling using feedforward
neural networks
: they take a random input ve
→