AI models
MLP with back-propagation
Training compute
6.7×10⁸ FLOP
Parameters
720
Published
Oct 1, 1986
MLP with back-propagation is an AI model developed by University of California San Diego and Carnegie Mellon University (CMU) (United States), first published in October 1986. It works in the mathematics domain, on tasks such as triplet completion. It counts among the frontier models: the systems trained with the most compute of their moment.
Training it took an estimated 6.7×10⁸ FLOP of compute (estimation method: operation counting). The model has 720 parameters. It was trained on roughly 104 datapoints.
The reference paper has 29,621 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of California San Diego, Carnegie Mellon University (CMU)
- Country of organization
- United States
- Domain
- Mathematics
- Task
- Triplet completion
- Training compute
- 6.7×10⁸ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 720
- Dataset size
- 104
- Citations
- 29,621
- Epoch confidence
- Confident
More from University of California San Diego,Carnegie Mellon University (CMU)
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