korrents

Our readingWhat is a korrent?

Depth is not free: past a point, deeper neural networks are harder to train rather than simply better.

Drawn from what Jian Sun and Kaiming He said

Subjectneural networks
What this subject means

neural networks The architecture almost all modern machine learning is built on, and what changes when it gets deeper.

Mental modelS-curves and diminishing returns

What they actually said

  1. Jian Sun Computer vision researcher Deeper neural networks are more difficult to train. He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org · 10 Dec 2015All 8 korrents from this piece
    Their wordsDeeper neural networks are more difficult to train.

    Where this was said

    ↗He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org

    10 Dec 2015

    All 8 korrents from this piecethis one is 2nd

  2. Kaiming He Associate professor at MIT and first author of the residual networks paper Deeper neural networks are more difficult to train. He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org · 10 Dec 2015All 8 korrents from this piece
    Their wordsDeeper neural networks are more difficult to train.

    Where this was said

    ↗He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org

    10 Dec 2015

    All 8 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