Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ Learning latent space representations of data remains to be an important task in
|
|
| 14 |
|
| 15 |
To learn discrete latent representations, ideas from vector quantisation (VQ) are used. Using the VQ method allows the model to avoid issues of ["posterior collapse"](https://datascience.stackexchange.com/questions/48962/what-is-posterior-collapse-phenomenon). By pairing these representations with an autoregressive prior, VQ-VAE models can generate high quality images, videos, speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
### Further learning
|
| 18 |
This model has been trained using code from this [example](https://keras.io/examples/generative/vq_vae/), and a result of this [paper.](https://arxiv.org/pdf/1711.00937.pdf)
|
| 19 |
|
|
|
|
| 14 |
|
| 15 |
To learn discrete latent representations, ideas from vector quantisation (VQ) are used. Using the VQ method allows the model to avoid issues of ["posterior collapse"](https://datascience.stackexchange.com/questions/48962/what-is-posterior-collapse-phenomenon). By pairing these representations with an autoregressive prior, VQ-VAE models can generate high quality images, videos, speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.
|
| 16 |
|
| 17 |
+
Full Credits for this example go to [Sayak Paul](https://twitter.com/RisingSayak)
|
| 18 |
+
|
| 19 |
### Further learning
|
| 20 |
This model has been trained using code from this [example](https://keras.io/examples/generative/vq_vae/), and a result of this [paper.](https://arxiv.org/pdf/1711.00937.pdf)
|
| 21 |
|