Adversarially Regularized Autoencoders for Generating Discrete Structures

Junbo Jake Zhao
Junbo Jake Zhao
Kelly Zhang
Kelly Zhang

arXiv: Learning, Volume abs/1706.04223, 2017.

Cited by: 10|Bibtex|Views128
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

Generative adversarial networks are an effective approach for learning rich latent representations of continuous data, but have proven difficult to apply directly to discrete structured data, such as text sequences or discretized images. Ideally we could encode discrete structures in a continuous code space to avoid this problem, but it i...More

Code:

Data:

Your rating :
0

 

Tags
Comments