Two Stage Feature Extraction (MNIST)

Training compute

2.1×10¹³ FLOP

Parameters

258.8K

Published

Sep 1, 2009

Two Stage Feature Extraction (MNIST) is an AI model developed by New York University (NYU) (United States), first published in September 2009. It works in the vision domain, on tasks such as image classification.

Training it took an estimated 2.1×10¹³ FLOP of compute (estimation method: operation counting). The model has 258,800 parameters. It was trained on roughly 50K 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: 2.1×10¹³ FLOP
Compute estimation method: Operation counting
Parameters: 258,800
Dataset size: 50K
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident