ADALINE
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
- Stanford University
- Organisation type
- Academia
- Country
- United States of America
- Published
- 30 June 1960
- Authors
- Widrow and Hoff
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Pattern recognition
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.
- Parameters
- 0K
- Training data
- 100 tokens
"The machine's total experience is stored in the values of the weights a0,...,a16"
"The best system, arrived at by slow precise adaptation on the full body of 100 noisy patterns, was able to classify these patterns as desired except for twelve errors." https://isl.stanford.edu/~widrow/papers/c1960adaptiveswitching.pdf
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
- 6.6 × 10³ FLOP
- How it was established
- Operation counting
"The method of searching that has proven most useful is the method of steepest descent" Apparently each pattern was only shown once to the system. So the training compute is (forward pass compute) * (3 for backprop) * dataset size This is a single layer (and single neuron) which does not require gradients w.r.t. inputs - 1:1 forward-backward ratio
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
- Highly cited
- Record confidence
- Confident
- Citations
- 6,329
Sources
Where this record came from and when it was last checked.
- Reference
- Adaptive switching circuits
- Last updated
- 28 November 2025
What the numbers mean
About this model
ADALINE was published by Stanford University, in the country recorded as United States of America, during June 1960. The publishing organisation is categorised as academia.
It works in the domain of Vision, and is recorded as performing the task of pattern recognition.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
The training run consumed about 6.6 × 10³ 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 100 tokens of text.
Its inclusion criterion: highly cited.
Answers
ADALINE — common questions
ADALINE— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of pattern recognition. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
ADALINE— how much compute was used to train it?
Training consumed around 6.6 × 10³ 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.
ADALINE— 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.
ADALINE— 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.
ADALINE— how many parameters does it have?
It has a parameter count of 0K. "The machine's total experience is stored in the values of the weights a0,...,a16". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
ADALINE— who created it?
It was published by Stanford University, based in United States of America, an organisation categorised as academia.
ADALINE— when was it released?
It was published in June 1960. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.