AI models
Mixture of linear models
Training compute
4.5×10¹¹ FLOP
Parameters
384K
Published
Dec 2, 1994
Mixture of linear models is an AI model, first published in December 1994. It works in the vision domain, on tasks such as image classification.
Training it took an estimated 4.5×10¹¹ FLOP of compute (estimation method: hardware). The model has 384,000 parameters. It was trained on roughly 1.8M datapoints.
Epoch AI rates the confidence of this record as likely.
Full record
- Domain
- Vision
- Task
- Image classification
- Training compute
- 4.5×10¹¹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 384,000
- Dataset size
- 1.8M
- Training time
- 12 h
- Epoch confidence
- Likely
More ai models
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