AI models
PoE MNIST
Training compute
5.2×10¹³ FLOP
Parameters
3.9M
Published
Nov 28, 2000
PoE MNIST is an AI model developed by University College London (UCL) (United Kingdom), first published in November 2000. It works in the vision domain, on tasks such as digit recognition. It counts among the frontier models: the systems trained with the most compute of their moment.
Training it took an estimated 5.2×10¹³ FLOP of compute (estimation method: operation counting). The model has 3,925,310 parameters. It was trained on roughly 54K datapoints.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University College London (UCL)
- Country of organization
- United Kingdom
- Domain
- Vision
- Task
- Digit recognition
- Training compute
- 5.2×10¹³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 3,925,310
- Dataset size
- 54K
- Epoch confidence
- Confident
More from University College London (UCL)
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