方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 归一化流× | 变分自编码器× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2015 | 2014 |
| 提出者≠ | Danilo Rezende & Shakir Mohamed | Kingma, D. P. & Welling, M. |
| 类型≠ | Generative model via invertible transformations | Deep generative latent-variable model (encoder–decoder) |
| 开创性文献≠ | Rezende, D. J., & Mohamed, S. (2015). Variational inference with normalizing flows. International Conference on Machine Learning (ICML), 1530–1538. link ↗ | Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗ |
| 别名 | Flow-Based Generative Models, Invertible Neural Networks, Exact Likelihood Models, Akışa Dayalı Üretici Modeller | Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model |
| 相关≠ | 2 | 5 |
| 摘要≠ | Normalizing flows are a class of generative models that learn a complex probability distribution by applying a sequence of invertible, differentiable transformations to a simple base distribution such as a standard Gaussian. Introduced by Rezende and Mohamed (2015) in the context of variational inference, they enable exact likelihood computation and efficient sampling, making them a principled alternative to VAEs and GANs for density estimation and generation tasks. | The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning. |
| ScholarGate数据集 ↗ |
|
|