Sparse Vision Encoding

Training compute

9.6×10¹² FLOP

Published

Nov 1, 2006

Sparse Vision Encoding is an AI model developed by Stanford University (United States), first published in November 2006. It works in the vision domain, on tasks such as image classification.

Training it took an estimated 9.6×10¹² FLOP of compute (estimation method: hardware).

Access: Unreleased. Its weights are not openly released. The reference paper has 3,512 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Stanford University
Country of organization: United States
Domain: Vision
Task: Image classification
Training compute: 9.6×10¹² FLOP
Compute estimation method: Hardware
Training time: 10 h
Model accessibility: Unreleased
Open weights: No
Citations: 3,512
Epoch confidence: Likely