AI models
Feedforward NN
Training compute
3.5×10¹⁴ FLOP
Parameters
7.1M
Published
May 13, 2010
Feedforward NN is an AI model developed by University of Montreal / Université de Montréal (Canada), first published in May 2010. It works in the vision domain, on tasks such as digit recognition.
Training it took an estimated 3.5×10¹⁴ FLOP of compute (estimation method: operation counting). The model has 7,082,000 parameters. It was trained on roughly 90K datapoints.
The reference paper has 18,606 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Montreal / Université de Montréal
- Country of organization
- Canada
- Domain
- Vision
- Task
- Digit recognition
- Training compute
- 3.5×10¹⁴ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 7,082,000
- Dataset size
- 90K
- Citations
- 18,606
- Epoch confidence
- Confident
More from University of Montreal / Université de Montréal
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