AI models
Ceramic-MLP
Training compute
4.5×10⁹ FLOP
Parameters
1.9K
Published
Jan 7, 1994
Ceramic-MLP is an AI model developed by Sapienza Università di Roma (Italy), first published in January 1994. It works in the materials science domain, on tasks such as pattern classification.
Training it took an estimated 4.5×10⁹ FLOP of compute (estimation method: operation counting). The model has 1,888 parameters. It was trained on roughly 80 datapoints.
Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Sapienza Università di Roma
- Country of organization
- Italy
- Domain
- Materials science
- Task
- Pattern classification
- Training compute
- 4.5×10⁹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 1,888
- Dataset size
- 80
- Epoch confidence
- Likely
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