Linear Decision Functions

Training compute

1.6×10⁶ FLOP

Published

Jun 1, 1962

Linear Decision Functions is an AI model developed by Bell Laboratories (United States), first published in June 1962. It works in the mathematics domain, on tasks such as binary classification. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 1.6×10⁶ FLOP of compute (estimation method: hardware). It was trained on roughly 500 datapoints.

Epoch AI rates the confidence of this record as speculative.

Full record

Organization: Bell Laboratories
Country of organization: United States
Domain: Mathematics
Task: Binary classification
Training compute: 1.6×10⁶ FLOP
Compute estimation method: Hardware
Dataset size: 500
Training time: 0 h
Epoch confidence: Speculative