Invariant CNN

Training compute

9.7×10¹¹ FLOP

Parameters

90.6K

Published

Jun 27, 2004

Invariant CNN is an AI model developed by New York University (NYU) (United States), first published in June 2004. It works in the vision domain, on tasks such as object recognition.

Training it took an estimated 9.7×10¹¹ FLOP of compute (estimation method: operation counting). The model has 90,575 parameters. It was trained on roughly 24.3K datapoints.

Epoch AI rates the confidence of this record as confident.

Full record

Organization: New York University (NYU)
Country of organization: United States
Domain: Vision
Task: Object recognition
Training compute: 9.7×10¹¹ FLOP
Compute estimation method: Operation counting
Parameters: 90,575
Dataset size: 24.3K
Epoch confidence: Confident