Dimensionality Reduction

Closed weights University of Toronto 3.8M parameters July 2006

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
University of Toronto
Organisation type
Academia
Country
Canada
Published
18 July 2006
Authors
GE Hinton, RR Salakhutdinov

What it does

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

Domain
Vision
Task
Face 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
3.8M
Training data
47,040,000 tokens

After fine-tuning on all 60,000 training images, the autoencoder was tested on 10,000 new images and produced much better reconstructions than did PCA (Fig. 2B)

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
15,697

Sources

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

Reference
Reducing the dimensionality of data with neural networks.
Last updated
28 November 2025

What the numbers mean

What this model is

Dimensionality Reduction was published by University of Toronto, in Canada, in July 2006. academia is the category the publisher falls under.

It works in Vision, and is recorded as doing face recognition.

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

Training and provenance

It was trained on about 47,040,000 tokens of text.

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

Answers

Dimensionality Reduction — common questions

01

What GPU do I need to run Dimensionality Reduction?

None. Dimensionality Reduction 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 Dimensionality Reduction open source?

The licensing for Dimensionality Reduction 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 Dimensionality Reduction have?

Dimensionality Reduction has 3.8M 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.

04

Who created Dimensionality Reduction?

Dimensionality Reduction was published by University of Toronto, based in Canada, categorised as academia.

05

When was Dimensionality Reduction released?

Dimensionality Reduction was published in July 2006. 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 Dimensionality Reduction used for?

Dimensionality Reduction works in Vision, and is recorded as handling face recognition. These are the areas it was designed around; they describe intent rather than a hard boundary.

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.