Kohonen network

Closed weights Helsinki University of Technology 4.1K parameters July 1981

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
Helsinki University of Technology
Organisation type
Academia
Country
Finland
Published
25 July 1981
Authors
T Kohonen

What it does

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

Domain
Mathematics
Task
Dimensionality reduction

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
4.1K

The input vectors are 3D. I could not find the grid size, but from the images it looks 8x8. So the network was 8x8x3 parameters.

Training data
4,000 tokens

??? Seemingly no info

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
Highly cited
Citations
11,841

Sources

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

Reference
Self-organized formation of topologically correct feature maps
Last updated
28 November 2025

What the numbers mean

About this model

Kohonen network was published by Helsinki University of Technology, in the country recorded as Finland, during July 1981. It comes out of an organisation categorised as academia.

It works in the domain of Mathematics, and is recorded as performing the task of dimensionality reduction.

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

Training and provenance

Training consumed a corpus of around 4,000 tokens of text.

The reason it appears in this catalogue at all: highly cited.

Answers

Kohonen network — common questions

01

Kohonen network— what is it used for?

It works in the domain of Mathematics, and is recorded as handling the task of dimensionality reduction. 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.

02

Kohonen network— 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.

03

Kohonen network— 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.

04

Kohonen network— how many parameters does it have?

It has a parameter count of 4.1K. The input vectors are 3D. I could not find the grid size, but from the images it looks 8x8. So the network was 8x8x3 parameters. 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.

05

Kohonen network— who created it?

It was published by Helsinki University of Technology, based in Finland, an organisation categorised as academia.

06

Kohonen network— when was it released?

It was published in July 1981. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.