AI models
6-layer MLP (MNIST)
Training compute
1.3×10¹⁴ FLOP
Parameters
12.1M
Published
Mar 1, 2010
6-layer MLP (MNIST) is an AI model developed by IDSIA, University of Lugano and SUPSI (Switzerland), first published in March 2010. It works in the vision domain, on tasks such as character recognition (ocr).
Training it took an estimated 1.3×10¹⁴ FLOP of compute (estimation method: operation counting). The model has 12,110,000 parameters. It was trained on roughly 60K datapoints. Training ran on NVIDIA GeForce GTX 280,Intel Core 2 Quad Q9450 for about 2 hours.
The reference paper has 1,264 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- IDSIA, University of Lugano, SUPSI
- Country of organization
- Switzerland
- Domain
- Vision
- Task
- Character recognition (OCR)
- Training compute
- 1.3×10¹⁴ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 12,110,000
- Dataset size
- 60K
- Training hardware
- NVIDIA GeForce GTX 280, Intel Core 2 Quad Q9450
- Training time
- 2 h
- Numerical format
- FP32
- Citations
- 1,264
- 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