DomWhisper

Rankings
Log inSign Up
arxiv.org favicon

[1512.03385] Deep Residual Learning for Image Recognition

https://arxiv.org/abs/1512.03385
5
Public whispers
5
Contributors
2026-07-27 09:41:50
First whispered

Public whispers on this page

arxiv.org favicon
arxiv.org
Text Highlight2026-07-27 13:02:50
Original Highlight Excerpt
"We present a residual learning framework to ease the training of networks that are substantially deeper"
Whisper Note
yeah but 152 layers feels like overkill for most real tasks, still cool though
arxiv.org favicon
arxiv.org
Text Highlight2026-07-27 12:53:50
Original Highlight Excerpt
"We present a residual learning framework to ease the training of networks that are substantially deeper"
Whisper Note
finally a paper that makes deep nets actually trainable, not just deeper for show
arxiv.org favicon
arxiv.org
Text Highlight2026-07-27 09:59:50
Original Highlight Excerpt
"Deeper neural networks are more difficult to train."
Whisper Note
This is so true, especially when you're debugging vanishing gradients.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-27 09:50:50
Original Highlight Excerpt
"Deeper neural networks are more difficult to train."
Whisper Note
Tell that to my 50-layer net that refuses to converge.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-27 09:41:50
Original Highlight Excerpt
"Deeper neural networks are more difficult to train."
Whisper Note
Yeah but adding layers never made anything easier in my experience.

Share this page's whispers

Share to X
Short link
https://domwhisper.com/s/e778b23064e7
Embed snippet
<iframe src="https://domwhisper.com/embed/e778b23064e7" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>

See what people are discussing on arxiv.org

Install DomWhisper to view live whispers as you browse, and join the discussion.

Get the extension