AI models
ADAM (CIFAR-10)
Training compute
6.2×10¹⁴ FLOP
Parameters
2.4M
Published
Dec 22, 2014
ADAM (CIFAR-10) is an AI model developed by University of Amsterdam, OpenAI and University of Toronto (Netherlands, United States and Canada), first published in December 2014. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 6.2×10¹⁴ FLOP of compute (estimation method: third-party estimation,operation counting). The model has 2,370,000 parameters. It was trained on roughly 50K datapoints.
Access: Unreleased. Its weights are not openly released. The reference paper has 166,267 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Amsterdam, OpenAI, University of Toronto
- Country of organization
- Netherlands, United States, Canada
- Domain
- Vision
- Task
- Image classification
- Training compute
- 6.2×10¹⁴ FLOP
- Compute estimation method
- Third-party estimation, Operation counting
- Parameters
- 2,370,000
- Dataset size
- 50K
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 166,267
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models