Distributed representation NN

Closed weights Carnegie Mellon University (CMU) 0.4K parameters August 1986

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
Carnegie Mellon University (CMU)
Organisation type
Academia
Country
United States of America
Published
15 August 1986
Authors
Geoffrey E. Hinton

What it does

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

Domain
Other
Task
Representation learning

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
0.4K

Parameters: 24*6 + 12*6 + 12*12 + 12*6 =432 "Figure 5: The activity levels in a five-layer network after it has learned. The bottom layer has 24 input units on the left for representing person 1 and 12 units on the right for representing the relationship. The white squares inside these two groups show the activity levels of the units. There is one active unit in the first group (representing Colin) and one in the second group (representing has-aunt). Each of the two groups of input units is tota…

Training data
100 tokens

"After 1500 sweeps through all 100 training examples the weights were very stable "

Epochs
1,500

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
3.9 × 10⁸ FLOP

2*432*3*1500*100=388800000=3.9e8 "After 1500 sweeps through all 100 training examples the weights were very stable "

How it was established
Operation counting

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,Highly cited
Record confidence
Confident

Sources

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

Reference
Learning distributed representations of concepts.
Last updated
28 November 2025

What the numbers mean

Where it came from

Distributed representation NN was published by Carnegie Mellon University (CMU), in United States of America, in August 1986. It comes out of academia.

It works in Other, and is recorded as doing representation learning.

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

How it was trained

The training run consumed about 3.9 × 10⁸ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 100 tokens went into training it.

Its inclusion criterion is historical significance,Highly cited.

Answers

Distributed representation NN — common questions

01

Is Distributed representation NN open source?

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

02

How many parameters does Distributed representation NN have?

Distributed representation NN has 0.4K parameters. Parameters: 24*6 + 12*6 + 12*12 + 12*6 =432 "Figure 5: The activity levels in a five-layer network after it has learned. The bottom layer has 24 input units on the left for representing person 1 and 12 units on the right for representing the relationship. The white squares inside these two groups show the activity levels of the units. There is one active unit in the first group (representing Colin) and one in the second group (representing has-aunt). Each of the two groups of input units is totally connected to its own group of 6 units in the second layer. These two groups of 6 must learn to encode the input terms as distributed patterns of activity. The second layer is totally connected to the central layer of 12 units, and this layer is connected to the penultimate layer of 6 units.". 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.

03

Who created Distributed representation NN?

Distributed representation NN was published by Carnegie Mellon University (CMU), based in United States of America, categorised as academia.

04

When was Distributed representation NN released?

Distributed representation NN was published in August 1986. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Distributed representation NN used for?

Distributed representation NN works in Other, and is recorded as handling representation learning. 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.

06

How much compute was used to train Distributed representation NN?

Around 3.9 × 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.

07

What GPU do I need to run Distributed representation NN?

None. Distributed representation NN 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.

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.