Deep Belief Nets
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,National University of Singapore
- Organisation type
- Academia,Academia
- Country
- Canada, Singapore
- Published
- 18 July 2006
- Authors
- GE Hinton, S Osindero, YW Teh
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Character recognition (OCR)
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
- 1.6M
- Training data
- 47,100,000 tokens
- Epochs
- 330
"The network that performed best on the validation set was then tested and had an error rate of 1.39%. This network was then trained on all 60,000 training images8 until its error-rate on the full training set was as low as its final error-rate had been on the initial training set of 44,000 images."
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 168 hours (7 days)
"a further 59 epochs [of training] making the total learning time about a week"
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
- 16,071
Sources
Where this record came from and when it was last checked.
- Reference
- A fast learning algorithm for deep belief nets
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Deep Belief Nets was published by University of Toronto,National University of Singapore, in the country recorded as Canada, during July 2006. It comes out of an organisation categorised as academia,Academia.
It works in the domain of Vision, and is recorded as performing the task of character recognition (OCR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
It was trained on a corpus of about 47,100,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: highly cited.
Answers
Deep Belief Nets — common questions
Deep Belief Nets— how many parameters does it have?
It has a parameter count of 1.6M. 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.
Deep Belief Nets— who created it?
It was published by University of Toronto,National University of Singapore, based in Canada, an organisation categorised as academia,Academia.
Deep Belief Nets— when was it released?
It 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.
Deep Belief Nets— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of character recognition (OCR). A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
Deep Belief Nets— 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.
Deep Belief Nets— 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.
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.