Credibilty Network
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 College London (UCL),University of Toronto
- Organisation type
- Academia,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, Canada
- Published
- 1 July 1999
- Authors
- Geoffrey E. Hinton, Zoubin Ghahramani, Vee Whye Tah
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Character recognition (OCR), Image 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
- 0.3K
- Training data
- 2,800 tokens
The size of the credibility network is 256-64-4. The 64 middle layer units are meant to encode low level features, while each of the 4 top level units are meant to encode a digit class
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
- 5.4 × 10⁶ FLOP
- How it was established
- Operation counting
=6*324 parameters *2800 datapoints
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.
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- Learning to Parse Images
- Last updated
- 28 November 2025
What the numbers mean
About this model
Credibilty Network was published by University College London (UCL),University of Toronto, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during July 1999. The category the publisher falls under is academia,Academia.
It works in the domain of Vision, and is recorded as performing the task of character recognition (OCR), Image classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The training run consumed about 5.4 × 10⁶ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 2,800 tokens of text.
Answers
Credibilty Network — common questions
Credibilty Network— 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.
Credibilty Network— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Credibilty Network— how many parameters does it have?
It has a parameter count of 0.3K. The size of the credibility network is 256-64-4. The 64 middle layer units are meant to encode low level features, while each of the 4 top level units are meant to encode a digit class. 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.
Credibilty Network— who created it?
It was published by University College London (UCL),University of Toronto, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as academia,Academia.
Credibilty Network— when was it released?
It was published in July 1999. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Credibilty Network— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of character recognition (OCR), Image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
Credibilty Network— how much compute was used to train it?
Training consumed around 5.4 × 10⁶ 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.
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.