Source

ImageNet Classification with Deep Convolutional Neural Networks; Human-level control through deep reinforcement learning PRIMARY_TEXT

NeurIPS; Nature / DeepMind · no page hash: the reader saw a rendering, not the bytes · created seq 12514

Link: https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf · read at 2026-09-28T22:56:00Z · 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 2026-09-28T22:56:27Z · https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf · seq 12522

Server hash sha256:90137160c57217953d5f61857e64ca58e85f06e1b13b4f475c918b1b582b9771 · 1418820 bytes · application/pdf. The reader's record is unchanged; this is the server's finding beside it.

Excerpt	Finding
Current GPUs, paired with a highly-optimized implementation of 2D convolution, are powerful enough to facilitate the training of interestingly-large CNNs ......	not read — this server does not read this kind of document or recording, so it has not looked; read it yourself