DBN for NLP

Closed weights Microsoft,University of Toronto 1M parameters February 2014

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
Microsoft,University of Toronto
Organisation type
Industry,Academia
Country
United States of America, Canada
Published
11 February 2014
Authors
R Sarikaya, GE Hinton, A Deoras

What it does

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

Domain
Language
Task
Text classification

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
1M

Assuming 1000 input features, 35 classes and 3 hidden layers of 500 units each

Training data
27,000 tokens

The training data has 27K automatically transcribed utterances amounting to 178K words.

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Citations
445

Sources

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

Reference
Application of Deep Belief Networks for Natural Language Understanding
Last updated
28 November 2025

What the numbers mean

What this model is

DBN for NLP was published by Microsoft,University of Toronto, in United States of America, in February 2014. The organisation is categorised as industry,Academia.

It works in Language, and is recorded as doing text classification.

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

How it was trained

It was trained on about 27,000 tokens of text.

Answers

DBN for NLP — common questions

01

How many parameters does DBN for NLP have?

DBN for NLP has 1M parameters. Assuming 1000 input features, 35 classes and 3 hidden layers of 500 units each. 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

Who created DBN for NLP?

DBN for NLP was published by Microsoft,University of Toronto, based in United States of America, categorised as industry,Academia.

03

When was DBN for NLP released?

DBN for NLP was published in February 2014. 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

What is DBN for NLP used for?

DBN for NLP works in Language, and is recorded as handling text classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

What GPU do I need to run DBN for NLP?

None. DBN for NLP 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

Is DBN for NLP open source?

The licensing for DBN for NLP 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.