korrents

A korrentour readingWhat is a korrent?

A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.

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 To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 16th

  2. Łukasz Kaiser To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 15th

  3. Aidan N. Gomez To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 14th

  4. Llion Jones To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 13th

  5. Jakob Uszkoreit To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 12th

  6. Niki Parmar To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 11th

  7. Noam Shazeer To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 10th

  8. Ashish Vaswani To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution. arxiv.org

    One of the eight authors of the 2017 transformer paper…

    Their wordsTo the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.

    Where this was said

    ↗Attention is all you needarxiv.org

    All 24 korrents from this piecethis one is 9th

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 →