korrents

What Kaiming He thinks about neural networks

@kaiming-he · 4 positions · 0 changes of mind

Associate professor at MIT and first author of the residual networks paper, the most cited paper in modern computer vision. Previously at Meta AI Research and Microsoft Research Asia.

Everything they publish, on ppll ↗

Kaiming He did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

2 dated positions, 2015, in their own words. Our reading of what Kaiming He has said — not written or endorsed by them.

2 positions so far — this page is not yet offered to search engines.

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

    Their wordsDeeper neural networks are more difficult to train.

    ↗He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org 1st of 8 in this piece

  3. Our readingResidual networks are easier to optimize than plain ones and keep gaining accuracy as depth increases.

    Their wordsWe provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

    ↗He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)arxiv.org 5th of 8 in this piece