方法证据记录
Variational Autoencoder
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.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Variational Autoencoder (VAE)
分类方法记录 · ml-model / deep-learning
- Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). · URL
- Higgins, I. et al. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations (ICLR). · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。