Siamese-TDNN

Training compute

1.3×10¹³ FLOP

Parameters

744

Published

Aug 1, 1993

Siamese-TDNN is an AI model developed by Bell Laboratories (United States), first published in August 1993. 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 1.3×10¹³ FLOP of compute (estimation method: operation counting). The model has 744 parameters. It was trained on roughly 7.7K datapoints.

Epoch AI rates the confidence of this record as likely.

Full record

Organization: Bell Laboratories
Country of organization: United States
Domain: Vision
Task: Image classification
Training compute: 1.3×10¹³ FLOP
Compute estimation method: Operation counting
Parameters: 744
Dataset size: 7.7K
Epoch confidence: Likely