Neural Foundations · 2012
AlexNet: ImageNet Classification with Deep CNNs
Showed that a large deep convolutional network trained on GPUs could win the ImageNet classification benchmark by a wide margin, demonstrating that scale of data, model, and compute together made deep learning practical for large-scale image recognition.
Editorial record
Plain-language summary
AlexNet is a deep convolutional network with roughly 60 million parameters trained on over a million labeled images across 1,000 categories, using ReLU activations for faster training, dropout to limit overfitting, data augmentation, and two GPUs to fit the model in memory. Combining these let it cut the ImageNet top-5 error far below the previous best. Its result shifted computer vision toward deep learning and drove wide adoption of GPU-trained convolutional networks.
Knowledge graph
Relationships
Antecedents
ChallengesEvidence: Strongly supported
Vision Transformer (An Image is Worth 16x16 Words)
ViT re-solves vision without convolution
P-300
Descendants
ExtendsEvidence: Strongly supported
LeNet: Gradient-Based Learning Applied to Document Recognition
LeNet CNN scaled up by AlexNet
A-019
Depends onEvidence: Strongly supported
Rectified Linear Units (ReLU)
AlexNet used ReLU
A-019
EnablesEvidence: Direct
ImageNet: A Large-Scale Hierarchical Image Database
AlexNet was trained and evaluated on the ImageNet dataset and challenge
AlexNet 2012
Source record
Provenance
- Record ID
- A-019
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.