Samuel Neural Checkers
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
- IBM
- Organisation type
- Industry
- Country
- United States of America
- Published
- 1 July 1959
- Authors
- Arthur L. Samuel
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Checkers
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
- tokens
"with 16 terms for generalization learning" "Mention has been made several times of the procedure for replacing terms in the scoring polynomial. The program, as it is currently running, contains 38 different terms (in addition to the piece-advantage term), 16 of these being included in the scoring polynomial at anyone time and the remaining 22 being kept in reserve."
Based on number of board positions At the present time the memory tape contains something over 53,000 board positions (averaging 3.8 word search) which have been selected from a much larger number of positions by means of the culling techniques described. While this is still far from the number which would tax the listing and searching procedures used in the program, rough estimates, based on the frequency with which the saved boards are utilized during normal play (these figures being tabulate…
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
- 4.3 × 10⁸ FLOP
"it can learn to do this in a remarkably short period of time 8 or 10 hours of machine-playing time)" "The availability of a larger and faster machine (the IBM 704), coupled with many detailed changes in the programming procedure, leads to a fairly interesting game being played, even without any learning." "The Type 704 is the first large-scale, commercially available computer to employ fully automatic floating point arithmetic commands. [...]. Floating point addition or subtraction operations…
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,Historical significance
- Record confidence
- Likely
- Citations
- 5,063
Sources
Where this record came from and when it was last checked.
- Reference
- Some studies in machine learning using the game of checkers
- Last updated
- 1 January 2026
What the numbers mean
Background
Samuel Neural Checkers was published by IBM, in United States of America, in July 1959. industry is the category the publisher falls under.
It works in Games, and is recorded as doing checkers.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
The training run consumed about 4.3 × 10⁸ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
It is tracked in the underlying dataset for one reason in particular: highly cited,Historical significance.
Answers
Samuel Neural Checkers — common questions
What is Samuel Neural Checkers used for?
Samuel Neural Checkers works in Games, and is recorded as handling checkers. 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.
How much compute was used to train Samuel Neural Checkers?
Around 4.3 × 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.
What GPU do I need to run Samuel Neural Checkers?
None. Samuel Neural Checkers 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.
Is Samuel Neural Checkers open source?
The licensing for Samuel Neural Checkers was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Samuel Neural Checkers have?
Samuel Neural Checkers has 0K parameters. "with 16 terms for generalization learning" "Mention has been made several times of the procedure for replacing terms in the scoring polynomial. The program, as it is currently running, contains 38 different terms (in addition to the piece-advantage term), 16 of these being included in the scoring polynomial at anyone time and the remaining 22 being kept in reserve.". 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.
Who created Samuel Neural Checkers?
Samuel Neural Checkers was published by IBM, based in United States of America, categorised as industry.
When was Samuel Neural Checkers released?
Samuel Neural Checkers was published in July 1959. 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.