---
title: "ImageNet classification with deep convolutional neural networks"
authors:
  - "Alex Krizhevsky"
  - "Ilya Sutskever"
  - "Geoffrey E. Hinton"
year: 2017
venue: "Communications of the ACM (2017 reprint of NeurIPS 2012)"
arxiv: null
doi: "10.1145/3065386"
source: "https://doi.org/10.1145/3065386"
topics:
  - "alexnet"
  - "cnn"
  - "imagenet"
seed_rank: 949
seed_batch: "user-add-2026-08-13"
reviewed: "2026-08-13"
pool: "languages"
relevance_score: 8
lineage: categorical-deep-learning
cites:
  []
---

# ImageNet classification with deep convolutional neural networks

## One-sentence takeaway

AlexNet: the 2012 ImageNet CNN that opened modern deep learning — CACM 2017 reprint of the NeurIPS 2012 paper.

## Why it matters here

The CNN Weaves still has to broadcast. Historical root of the architecture zoo; ReLU + dropout + GPU training is the recipe that made depth practical.

## Key ideas

- NeurIPS 2012 original; CACM 60(6):84–90, May 2017 reprint. DOI `10.1145/3065386`.
- Deep convnet + ReLU + dropout + two-GPU training on ImageNet.
- Weaves cites the CACM reprint; year 2017 matches that venue.
- Reprint, not a new result. No categorical content.

## Caveats

## Links

- DOI: [10.1145/3065386](https://doi.org/10.1145/3065386)
- NeurIPS 2012: https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html