Kusner, MJ;
Hernández-Lobato, JM;
(2016)
GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution.
arXiv.org: Ithaca (NY), USA.
Preview |
Text
1611.04051v1.pdf - Accepted Version Download (828kB) | Preview |
Abstract
Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are not differentiable with respect to the distribution parameters. This problem can be avoided by using the Gumbel-softmax distribution, which is a continuous approximation to a multinomial distribution parameterized in terms of the softmax function. In this work, we evaluate the performance of GANs based on recurrent neural networks with Gumbel-softmax output distributions in the task of generating sequences of discrete elements.
| Type: | Working / discussion paper |
|---|---|
| Title: | GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://doi.org/10.48550/arXiv.1611.04051 |
| Language: | English |
| Additional information: | This version is the author manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10088324 |
Archive Staff Only
 |
View Item |
