High Performance CNN (NORB)

Training compute

2.6×10¹⁶ FLOP

Parameters

4.9M

Published

Jul 16, 2011

High Performance CNN (NORB) is an AI model developed by IDSIA and SUPSI (Switzerland), first published in July 2011. It works in the vision domain, on tasks such as image classification.

Training it took an estimated 2.6×10¹⁶ FLOP of compute (estimation method: hardware). The model has 4,878,300 parameters. It was trained on roughly 50K datapoints. Training ran on 4 NVIDIA GeForce GTX 480,NVIDIA GeForce GTX 580 for about 4 hours.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.

Full record

Organization: IDSIA, SUPSI
Country of organization: Switzerland
Domain: Vision
Task: Image classification
Training compute: 2.6×10¹⁶ FLOP
Compute estimation method: Hardware
Parameters: 4,878,300
Dataset size: 50K
Training hardware: NVIDIA GeForce GTX 480, NVIDIA GeForce GTX 580
Chips used: 4
Training time: 4 h
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Likely