Linear Decision Functions
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Bell Laboratories
- Organisation type
- Industry
- Country
- United States of America
- Published
- 1 June 1962
- Authors
- W. Highleyman
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Mathematics
- Task
- Binary classification
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- 500 tokens
"Fifty different people were asked, resulting in a sample size of 50 for each of the ten pattern classes. "
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.6 × 10⁶ FLOP
- How it was established
- Hardware
0.5*45*35*1980 = 1559250 = 1.56e6 Trained using IBM punched cards, computation took 45 * 35s for all 10 digits (Section Estimating the Linear Decision Function). Multiplications per second estimate based on publication year: 1.98e3 (regression on Nordhaus data). Assumed utilization of 0.5
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 0 hours
"Forty-five hyperplanes are required in the complete linear decision function" "About 35 seconds, on the average, was required to determine a hyperplane, given an initial position."
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Frontier model
- Yes
- Why it is tracked
- Historical significance,Highly cited
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- Linear Decision Functions, with Application to Pattern Recognition
- Last updated
- 28 November 2025
What the numbers mean
About this model
Linear Decision Functions was published by Bell Laboratories, in the country recorded as United States of America, during June 1962. The publishing organisation is categorised as industry.
It works in the domain of Mathematics, and is recorded as performing the task of binary classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Producing it required arithmetic totalling around 1.6 × 10⁶ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 500 tokens of text.
The reason it appears in this catalogue at all: historical significance,Highly cited.
Answers
Linear Decision Functions — common questions
Linear Decision Functions— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Linear Decision Functions— who created it?
It was published by Bell Laboratories, based in United States of America, an organisation categorised as industry.
Linear Decision Functions— when was it released?
It was published in June 1962. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Linear Decision Functions— what is it used for?
It works in the domain of Mathematics, and is recorded as handling the task of binary classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Linear Decision Functions— how much compute was used to train it?
Training consumed around 1.6 × 10⁶ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Linear Decision Functions— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Linear Decision Functions— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.