korrents

A korrentour readingWhat is a korrent?

Self-attention can yield more interpretable models.

Drawn from what Illia Polosukhin, Łukasz Kaiser and 6 others said

Subjecttransformers
What this subject means

transformers The architecture that dropped recurrence in favour of attention, and that almost every large model since is built on.

What they actually said

Word for word, with the source under each one. They did not write this page.

  1. Illia Polosukhin As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 24th

  2. Łukasz Kaiser As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 23rd

  3. Aidan N. Gomez As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 22nd

  4. Llion Jones As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 21st

  5. Jakob Uszkoreit As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 20th

  6. Niki Parmar As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 19th

  7. Noam Shazeer As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 18th

  8. Ashish Vaswani As side benefit, self-attention could yield more interpretable models. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsAs side benefit, self-attention could yield more interpretable models.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 17th

Added to korrents 12 Jun 2017 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

On the map

Loading the map… or open it on its own page

Open the map on its own page →