Hopfield network

Closed weights California Institute of Technology 9.9K parameters April 1982

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
California Institute of Technology
Organisation type
Academia
Country
United States of America
Published
1 April 1982
Authors
JJ Hopfield

What it does

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

Domain
Other
Task
Sequence memorization

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
9.9K

My understanding is that the biggest Hopfield networks they studied had N=100 units. Each unit has 99 synapses Tij from each other unit, for a total of 100*99 parameters

Training data
tokens

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
23,315

Sources

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

Reference
Neural networks and physical systems with emergent collective computational abilities
Last updated
28 November 2025

What the numbers mean

Where it came from

Hopfield network was published by California Institute of Technology, in the country recorded as United States of America, during April 1982. It comes out of an organisation categorised as academia.

It works in the domain of Other, and is recorded as performing the task of sequence memorization.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

It is tracked in the underlying dataset for one reason in particular: highly cited.

Answers

Hopfield network — common questions

01

Hopfield network— how many parameters does it have?

It has a parameter count of 9.9K. My understanding is that the biggest Hopfield networks they studied had N=100 units. Each unit has 99 synapses Tij from each other unit, for a total of 100*99 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.

02

Hopfield network— who created it?

It was published by California Institute of Technology, based in United States of America, an organisation categorised as academia.

03

Hopfield network— when was it released?

It was published in April 1982. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

Hopfield network— what is it used for?

It works in the domain of Other, and is recorded as handling the task of sequence memorization. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

Hopfield 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.

06

Hopfield 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.

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.