LISSOM

Training compute

2×10¹¹ FLOP

Parameters

432.8K

Published

Nov 27, 1995

LISSOM is an AI model developed by University of Texas at Austin (United States), first published in November 1995. It works in the vision domain, on tasks such as digit recognition.

Training it took an estimated 2×10¹¹ FLOP of compute (estimation method: operation counting). The model has 432,800 parameters. It was trained on roughly 2K datapoints.

Epoch AI rates the confidence of this record as likely.

Full record

Organization: University of Texas at Austin
Country of organization: United States
Domain: Vision
Task: Digit recognition
Training compute: 2×10¹¹ FLOP
Compute estimation method: Operation counting
Parameters: 432,800
Dataset size: 2K
Epoch confidence: Likely