Machine learningGenerative models
归一化流
归一化流是一类生成模型，它们通过对简单的基分布（如标准高斯分布）应用一系列可逆、可微的变换来学习复杂的概率分布。该模型由 Rezende 和 Mohamed (2015) 在变分推断的背景下提出，能够进行精确的似然计算和高效采样，使其成为密度估计和生成任务中变分自编码器 (VAE) 和生成对抗网络 (GAN) 的一种原则性替代方案。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Rezende, D. J., & Mohamed, S. (2015). Variational inference with normalizing flows. International Conference on Machine Learning (ICML), 1530–1538. link ↗
如何引用本页
ScholarGate. (2026, June 2). Normalizing Flows. ScholarGate. https://scholargate.app/zh/deep-learning/normalizing-flows
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →