SVM-CNN

Training compute

7.5×10¹⁴ FLOP

Parameters

90.9K

Published

Jun 17, 2006

SVM-CNN is an AI model developed by New York University (NYU) (United States), first published in June 2006. It works in the vision domain, on tasks such as image classification. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 7.5×10¹⁴ FLOP of compute (estimation method: hardware). The model has 90,857 parameters. It was trained on roughly 583.2K datapoints.

Access: Unreleased. Its weights are not openly released. 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: Image classification
Training compute: 7.5×10¹⁴ FLOP
Compute estimation method: Hardware
Parameters: 90,857
Dataset size: 583.2K
Chips used: 1
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident