From c3f44ae579f450016689e5453a9d786e95c41e3a Mon Sep 17 00:00:00 2001 From: Ravi Singh <59569106+singhravipratap@users.noreply.github.com> Date: Thu, 12 Sep 2024 00:42:57 +0530 Subject: [PATCH] Update README.md (#790) Add Attention is all You need Paper. Co-authored-by: Zeeshan Lakhani Co-authored-by: Eric Leung <2754821+erictleung@users.noreply.github.com> --- artificial_intelligence/README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/artificial_intelligence/README.md b/artificial_intelligence/README.md index 5924d89..d9a8fda 100644 --- a/artificial_intelligence/README.md +++ b/artificial_intelligence/README.md @@ -12,4 +12,6 @@ * [Mastering the Game of Go with Deep Neural Networks and Tree Search](http://airesearch.com/wp-content/uploads/2016/01/deepmind-mastering-go.pdf) by Silver et al. * [A Universal Music Translation Network (2018)](https://arxiv.org/pdf/1805.07848.pdf) by Noam Mor, Lior Wolf, Adam Polyak & Yaniv Taigman - > This paper proposes a method for translating music across musical instruments, genres, and styles. It is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-independent encoder enables translation even from musical domains that were not seen during training. The method is unsupervised and does not rely on supervision in the form of matched samples between domains or musical transcriptions. This method is evaluated on NSynth, as well as on a dataset collected from professional musicians, and achieve convincing translations, even when translating from whistling, potentially enabling the creation of instrumental music by untrained humans. \ No newline at end of file + > This paper proposes a method for translating music across musical instruments, genres, and styles. It is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-independent encoder enables translation even from musical domains that were not seen during training. The method is unsupervised and does not rely on supervision in the form of matched samples between domains or musical transcriptions. This method is evaluated on NSynth, as well as on a dataset collected from professional musicians, and achieve convincing translations, even when translating from whistling, potentially enabling the creation of instrumental music by untrained humans. + +* [Attention is all you need](http://papers.neurips.cc/paper/7181-attention-is-all-you-need.pdf) by Ashish Vaswani et al.