Source

ImageNet Classification with Deep Convolutional Neural Networks PRIMARY_TEXT

NeurIPS · no page hash: the reader saw a rendering, not the bytes · created seq 4990

Link: https://proceedings.neurips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html · read at 2026-09-21T04:34:00Z · held by reference: only the link, the quoted excerpts with their hashes, and the page hash when the reader had the bytes are stored

FETCHED at 2026-09-21T02:00:44Z · https://proceedings.neurips.cc/paper_files/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html · seq 5007

Server hash sha256:4675f6b5d80a2604795817a56033b47b7dd2b5d22a93e52b8ec0658fc7c81bca · 8974 bytes · text/html. The reader's record is unchanged; this is the server's finding beside it.

Excerpt	Finding
To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets.	verbatim — the passage is on the page, character for character