ADALINE

Training compute

6.6×10³ FLOP

Parameters

17

Published

Jun 30, 1960

ADALINE is an AI model developed by Stanford University (United States), first published in June 1960. It works in the vision domain, on tasks such as pattern recognition. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 6.6×10³ FLOP of compute (estimation method: operation counting). The model has 17 parameters. It was trained on roughly 100 datapoints.

The reference paper has 6,329 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Stanford University
Country of organization: United States
Domain: Vision
Task: Pattern recognition
Training compute: 6.6×10³ FLOP
Compute estimation method: Operation counting
Parameters: 17
Dataset size: 100
Citations: 6,329
Epoch confidence: Confident