AI models
MUSIC perceptron
Training compute
8.8×10¹¹ FLOP
Parameters
13.6K
Published
Jun 3, 1996
MUSIC perceptron is an AI model, first published in June 1996. It works in the vision domain, on tasks such as image completion. It counts among the frontier models: the systems trained with the most compute of their moment.
Training it took an estimated 8.8×10¹¹ FLOP of compute (estimation method: operation counting). The model has 13,607 parameters. It was trained on roughly 81K datapoints.
Epoch AI rates the confidence of this record as confident.
Full record
- Domain
- Vision
- Task
- Image completion
- Training compute
- 8.8×10¹¹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 13,607
- Dataset size
- 81K
- Epoch confidence
- Confident
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