Machine learning

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.

Open in MethodMindSoonVideoSoon

Read the full method

Members only

Sources

Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗
Higgins, I. et al. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations (ICLR). link ↗

Referenced by

Autoencoder Autoencoder Anomaly Detection Bayesian Gaussian Mixture Model Bayesian single-cell RNA-seq analysis Diffusion Model Domain-adaptive variational autoencoder Explainable GAN Explainable Gaussian Mixture Model Explainable Variational Autoencoder Fine-Tuned Variational Autoencoder Generative Adversarial Network GPT Fine-Tuning LoRA and PEFT Multilingual variational autoencoder Multimodal Variational Autoencoder Neural Style Transfer Normalizing Flows Restricted Boltzmann Machine Score-Based Generative Model Self-supervised Autoencoder Anomaly Detection Self-supervised Diffusion Model Self-supervised Gaussian Mixture Model Self-supervised Gaussian Process Self-supervised Variational Autoencoder Semi-supervised Diffusion Model Semi-supervised GAN Semi-supervised Gaussian Mixture Model Semi-supervised LSTM Semi-supervised Variational Autoencoder Transfer learning GAN Transfer learning variational autoencoder Vision Transformer Weakly Supervised Diffusion Model Weakly supervised GAN Weakly Supervised Variational Autoencoder

Spotted an issue on this page? Report or suggest a fix →

Read the full method

Sources

Related methods

Referenced by