Visualizing CNNs

Training compute

5.3×10¹⁷ FLOP

Published

Nov 12, 2013

Visualizing CNNs is an AI model developed by New York University (NYU) (United States), first published in November 2013. 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 5.3×10¹⁷ FLOP of compute (estimation method: hardware,third-party estimation). It was trained on roughly 7.7M datapoints. Training ran on NVIDIA GeForce GTX 580. The compute alone is estimated at $13 in 2023 dollars.

The reference paper has 17,026 citations. 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: 5.3×10¹⁷ FLOP
Compute estimation method: Hardware, Third-party estimation
Dataset size: 7.7M
Training hardware: NVIDIA GeForce GTX 580
Training cost (2023 USD): $13
Numerical format: FP32
Citations: 17,026
Epoch confidence: Confident