Dropout (MNIST)

Training compute

6×10¹⁵ FLOP

Parameters

5.6M

Published

Jun 3, 2012

Dropout (MNIST) is an AI model developed by University of Toronto (Canada), first published in June 2012. It works in the vision domain, on tasks such as character recognition (ocr).

Training it took an estimated 6×10¹⁵ FLOP of compute (estimation method: operation counting). The model has 5,594,010 parameters. It was trained on roughly 60K datapoints. Training ran on NVIDIA GeForce GTX 580.

Access: Unreleased. Its weights are not openly released. The reference paper has 7,999 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Vision
Task: Character recognition (OCR)
Training compute: 6×10¹⁵ FLOP
Compute estimation method: Operation counting
Parameters: 5,594,010
Dataset size: 60K
Training hardware: NVIDIA GeForce GTX 580
Model accessibility: Unreleased
Open weights: No
Citations: 7,999
Epoch confidence: Confident