MCDNN (MNIST)

Training compute

1.6×10¹⁶ FLOP

Parameters

2.7M

Published

Feb 13, 2012

MCDNN (MNIST) is an AI model developed by IDSIA and SUPSI (Switzerland), first published in February 2012. It works in the vision domain, on tasks such as character recognition (ocr) and image classification.

Training it took an estimated 1.6×10¹⁶ FLOP of compute (estimation method: operation counting). The model has 2,653,700 parameters. It was trained on roughly 2.1M datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 4,828 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: IDSIA, SUPSI
Country of organization: Switzerland
Domain: Vision
Task: Character recognition (OCR), Image classification
Training compute: 1.6×10¹⁶ FLOP
Compute estimation method: Operation counting
Parameters: 2,653,700
Dataset size: 2.1M
Model accessibility: Unreleased
Open weights: No
Citations: 4,828
Epoch confidence: Likely