korrents

Our readingWhat is a korrent?

Sequence transduction can use a simple architecture based solely on attention, without recurrence or convolutions.

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

  1. Illia Polosukhin One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 8th

  2. Łukasz Kaiser One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 7th

  3. Aidan N. Gomez One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 6th

  4. Llion Jones One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 5th

  5. Jakob Uszkoreit One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 4th

  6. Niki Parmar One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 3rd

  7. Noam Shazeer One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 2nd

  8. Ashish Vaswani One of the eight authors of the 2017 transformer paper… We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Attention is all you needarxiv.org · 12 Jun 2017All 24 korrents from this piece
    Their wordsWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

    Where this was said

    ↗Attention is all you needarxiv.org

    12 Jun 2017

    All 24 korrents from this piecethis one is 1st

Added to korrents 9 Sept 2026 · How quotes work · Something wrong? Tell us

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

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map