Sign in

Adversarial Autoencoders with Constant-Curvature Latent Manifolds

By Daniele Grattarola and others
Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like hierarchy and circularity. In this work, we introduce the CCM adversarial autoencoder (CCM-AAE), a probabilistic generative model trained to represent... Show more
April 11, 2019
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Adversarial Autoencoders with Constant-Curvature Latent Manifolds
Click on play to start listening