BatchNorm

Parameters

13.6M

Published

Jun 15, 2015

BatchNorm is an AI model developed by Google (United States), first published in June 2015. It works in the vision domain, on tasks such as image classification.

Epoch AI has no training-compute estimate for this model. The model has 13,600,000 parameters. It was trained on roughly 12.4B datapoints.

It is built on top of GoogLeNet / InceptionV1. The reference paper has 46,718 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google
Country of organization: United States
Domain: Vision
Task: Image classification
Parameters: 13,600,000
Dataset size: 12.4B
Base model: GoogLeNet / InceptionV1
Citations: 46,718
Epoch confidence: Confident