Self Organizing System

Closed weights Massachusetts Institute of Technology (MIT) 0.2K parameters March 1955

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
Massachusetts Institute of Technology (MIT)
Organisation type
Academia
Country
United States of America
Published
1 March 1955
Authors
W. A. Clark and B. G. Farley

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Other
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
0.2K

Figure 4 contains the learnt weight matrix

Training data
2 tokens

" The modifier was then disabled so that no further changes in the net could occur and all 256 possible input patterns were then presented in turn." "For these purposes, 16-element nets (8 input and 8 output) were used because it was desired to exhaust all possible input patterns, and we were limited to about 2^8 inputs by available time. "

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Historical significance
Citations
93

Sources

Where this record came from and when it was last checked.

Reference
Generalization of pattern recognition in a self-organizing system
Last updated
28 November 2025

What the numbers mean

Where it came from

Self Organizing System was published by Massachusetts Institute of Technology (MIT), in United States of America, in March 1955. The organisation is categorised as academia.

It works in Other, and is recorded as doing pattern recognition.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The training set ran to roughly 2 tokens.

The reason it appears in this catalogue at all is historical significance.

Answers

Self Organizing System — common questions

01

What GPU do I need to run Self Organizing System?

None. Self Organizing System 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.

02

Is Self Organizing System open source?

The licensing for Self Organizing System was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does Self Organizing System have?

Self Organizing System has 0.2K parameters. Figure 4 contains the learnt weight matrix. 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.

04

Who created Self Organizing System?

Self Organizing System was published by Massachusetts Institute of Technology (MIT), based in United States of America, categorised as academia.

05

When was Self Organizing System released?

Self Organizing System was published in March 1955. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is Self Organizing System used for?

Self Organizing System works in Other, and is recorded as handling 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.

Source

Original publication

Record last updated 28 November 2025

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.