ReLU (NORB)

Parameters

16.2M

Published

Jun 15, 2010

ReLU (NORB) is an AI model developed by University of Toronto (Canada), first published in June 2010. It works in the vision domain, on tasks such as object recognition.

Epoch AI has no training-compute estimate for this model. The model has 16,210,006 parameters. It was trained on roughly 291.6K datapoints.

The reference paper has 18,270 citations.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Vision
Task: Object recognition
Parameters: 16,210,006
Dataset size: 291.6K
Citations: 18,270