0
$\begingroup$

In a paper I'm reading today it's written :

For a fixed parameter count, we discover that large sparse WaveRNNs significantly outperform small dense WaveRNNs and that this relationship holds up to high level of sparsity greater than 96 %.

What does it all mean ? Does it have something to do with the number of layers ?

Improve this question
$\endgroup$
2
  • $\begingroup$ ... what paper? $\endgroup$
    – Sean Owen
    May 20, 2019 at 14:20
  • $\begingroup$ @SeanOwen Efficient Neural Audio Synthesis $\endgroup$
    – Vincent Brisse
    May 21, 2019 at 15:03

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.