308 citations · 486 across the 3 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2018★ 4 cited
Implicit Autoencoders
Alireza Makhzani
In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distri…
cs.LG2015★ 308 cited
Adversarial Autoencoders
Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly +2
In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform…
cs.LG2014★ 174 cited
Winner-Take-All Autoencoders
Alireza Makhzani, Brendan Frey
In this paper, we propose a winner-take-all method for learning hierarchical sparse representations in an unsupervised fashion. We first introduce fully-connected winner-take-all a…