An Introduction to Variational Autoencoders

[image error]These people don’t exist! (source)

Variational Autoencoders (VAE) are really cool machine learning models that can generate new data. It means a VAE trained on thousands of human faces can new human faces as shown above!

Recently, two types of generative models have been popular in the machine learning community, namely, Generative Adversarial Networks (GAN) and VAEs. While GANs have had more success so far, a recent Deepmind paper showed that VAEs can yield results competitive to state of...

 •  0 comments  •  flag
Share on Twitter
Published on January 31, 2020 23:15
No comments have been added yet.