GPU DBNs

Closed weights Stanford University 100M parameters June 2009

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
Stanford University
Organisation type
Academia
Country
United States of America
Published
15 June 2009
Authors
R Raina, A Madhavan, AY Ng

What it does

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

Domain
Other
Task
Miscellaneous image analysis
Numerical format
FP32

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
100M

"For example, we are able to reduce the time required to learn a four-layer DBN with 100 million free parameters from several weeks to around a single day."

Training data
121,344,000,000 tokens

Table 2 shows the running time for processing 1 million examples for RBMs of varying size

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
1 × 10¹⁵ FLOP

https://www.getguesstimate.com/models/19602 6435 GPU seconds for 1M examples Single GTX 280 with 622.1 GFLOPS All results are reported for 1M examples, unclear if they ran larger training experiments.

How it was established
Hardware

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,Historical significance
Record confidence
Confident
Citations
1,032

Sources

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

Reference
Large-scale Deep Unsupervised Learning using Graphics Processors
Last updated
28 November 2025

What the numbers mean

About this model

GPU DBNs was published by Stanford University, in the country recorded as United States of America, during June 2009. The category the publisher falls under is academia.

It works in the domain of Other, and is recorded as performing the task of miscellaneous image analysis.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

Training it took a computation budget of roughly 1 × 10¹⁵ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 121,344,000,000 tokens of text.

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

Answers

GPU DBNs — common questions

01

GPU DBNs— what is it used for?

It works in the domain of Other, and is recorded as handling the task of miscellaneous image analysis. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

GPU DBNs— how much compute was used to train it?

Training consumed around 1 × 10¹⁵ 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.

03

GPU DBNs— 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.

04

GPU DBNs— 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.

05

GPU DBNs— how many parameters does it have?

It has a parameter count of 100M. "For example, we are able to reduce the time required to learn a four-layer DBN with 100 million free parameters from several weeks to around a single day.". 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.

06

GPU DBNs— who created it?

It was published by Stanford University, based in United States of America, an organisation categorised as academia.

07

GPU DBNs— when was it released?

It was published in June 2009. 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.