Greedy layer-wise DNN training

Closed weights University of Montreal / Université de Montréal December 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 Montreal / Université de Montréal
Organisation type
Academia
Country
Canada
Published
4 December 2006
Authors
Y Bengio, P Lamblin, D Popovici

What it does

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

Domain
Other
Task
Image classification, Regression

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.

Training data
107,100,000 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
Record confidence
Unknown
Citations
5,605

Sources

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

Reference
Greedy layer-wise training of deep networks
Last updated
28 November 2025

What the numbers mean

About this model

Greedy layer-wise DNN training was published by University of Montreal / Université de Montréal, in Canada, in December 2006. The organisation is categorised as academia.

It works in Other, and is recorded as doing image classification, Regression.

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

Training and provenance

The training set ran to roughly 107,100,000 tokens.

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

Answers

Greedy layer-wise DNN training — common questions

01

Is Greedy layer-wise DNN training open source?

The licensing for Greedy layer-wise DNN training 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 Greedy layer-wise DNN training have?

No parameter count has been published for Greedy layer-wise DNN training, which is why no memory or speed figure appears on this page.

03

Who created Greedy layer-wise DNN training?

Greedy layer-wise DNN training was published by University of Montreal / Université de Montréal, based in Canada, categorised as academia.

04

When was Greedy layer-wise DNN training released?

Greedy layer-wise DNN training was published in December 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.

05

What is Greedy layer-wise DNN training used for?

Greedy layer-wise DNN training works in Other, and is recorded as handling image classification, Regression. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

What GPU do I need to run Greedy layer-wise DNN training?

None. Greedy layer-wise DNN training 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.