About us
Stay in touch
A neural network, introduced by Diederik Kingma and Max Welling in 2013, that compresses data into a smooth latent space and generates new examples by decoding points from it. It was one of the first deep generative models.
The person in that space is Durk Kingma, who ended up going to OpenAI. He's a super genius. He also did the Adam optimizer and a bunch of other foundational stuff at the time. But he did the variational autoencoder.