BP-DBN

Closed weights University of Toronto 18M parameters January 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
University of Toronto
Organisation type
Academia
Country
Canada
Published
1 January 2009
Authors
Abdel-rahman Mohamed, George Dahl, and Geoffrey Hinton

What it does

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

Domain
Speech
Task
Speech recognition (ASR)
Approach
Supervised

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
18M

429*2048+2048*2048*4+2048*183=18030592 Table 2: largest model has 5 layers of 2048 into 183 softmax, 429 input

Training data
tokens

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA Tesla S1070
Chips used
1
Power draw
984 W

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

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
Historical significance,SOTA improvement

"On the standard TIMIT corpus, DBNs consistently outperform other techniques and the best DBN achieves a phone error rate (PER) of 23.0% on the TIMIT core test set."

Record confidence
Confident

Sources

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

Reference
Deep Belief Networks for phone recognition
Last updated
28 November 2025

What the numbers mean

About this model

BP-DBN was published by University of Toronto, in Canada, in January 2009. academia is the category the publisher falls under.

It works in Speech, and is recorded as doing speech recognition (ASR).

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

Training and provenance

It is tracked in the underlying dataset for one reason in particular: historical significance,SOTA improvement.

Answers

BP-DBN — common questions

01

Who created BP-DBN?

BP-DBN was published by University of Toronto, based in Canada, categorised as academia.

02

When was BP-DBN released?

BP-DBN was published in January 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.

03

What is BP-DBN used for?

BP-DBN works in Speech, and is recorded as handling speech recognition (ASR). These are the areas it was designed around; they describe intent rather than a hard boundary.

04

What GPU do I need to run BP-DBN?

None. BP-DBN 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.

05

Is BP-DBN open source?

No. BP-DBN has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does BP-DBN have?

BP-DBN has 18M parameters. 429*2048+2048*2048*4+2048*183=18030592 Table 2: largest model has 5 layers of 2048 into 183 softmax, 429 input. 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.

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.