Importance Weighted Autoencoders
CoRR, Volume abs/1509.00519, 2015.
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximatel...More
PPT (Upload PPT)