Perceptron (1960)
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
- Cornell Aeronautical Laboratory
- Organisation type
- Academia
- Country
- United States of America
- Published
- 30 March 1960
- Authors
- Frank Rosenblatt
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image 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.
- Parameters
- 1K
- Training data
- 100 tokens
" The first program was designed to handle up to 1000 A units, and a 72 by 72 sensory mosaic. It was found that this large sensory system presented stimuli with a fineness of grain considerably better than the limits of discrimination of a thousand-unit percep- tron, and at the same time, required an excessive amount of time for stimulus transformations, since each illuminated point in the stimulus must be transformed individually into its image point."
from the text "The two main simulation programs total about 5000 words each."
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
- 7.2 × 10⁸ FLOP
- How it was established
- Hardware
4000 * 12000 * 15 from the text "This program uses the IBM 704 computer to simulate per-ceptual learning, recognition, and spontaneous classification of visual stimuli in the perceptron," from https://en.wikipedia.org/wiki/IBM_704 The 704 can execute up to 12,000 floating-point additions per second. " For the first system, the computing time averaged about 15 seconds per stimulus cycle, " In Fig 10 we see up to 4000 stimuli
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
- Record confidence
- Speculative
- Citations
- 394
Sources
Where this record came from and when it was last checked.
- Reference
- Perceptron Simulation Experiments
- Last updated
- 11 February 2026
What the numbers mean
About this model
Perceptron (1960) was published by Cornell Aeronautical Laboratory, in the country recorded as United States of America, during March 1960. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of image classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Producing it required arithmetic totalling around 7.2 × 10⁸ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 100 tokens of text.
Its inclusion criterion: historical significance.
Answers
Perceptron (1960) — common questions
Perceptron (1960)— how much compute was used to train it?
Training consumed around 7.2 × 10⁸ 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.
Perceptron (1960)— 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.
Perceptron (1960)— 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.
Perceptron (1960)— how many parameters does it have?
It has a parameter count of 1K. " The first program was designed to handle up to 1000 A units, and a 72 by 72 sensory mosaic. It was found that this large sensory system presented stimuli with a fineness of grain considerably better than the limits of discrimination of a thousand-unit percep- tron, and at the same time, required an excessive amount of time for stimulus transformations, since each illuminated point in the stimulus must be transformed individually into its image point.". 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.
Perceptron (1960)— who created it?
It was published by Cornell Aeronautical Laboratory, based in United States of America, an organisation categorised as academia.
Perceptron (1960)— when was it released?
It was published in March 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.
Perceptron (1960)— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.