CNN Committee (NIST)
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
- IDSIA
- Organisation type
- Academia
- Country
- Switzerland
- Published
- 18 September 2011
- Authors
- D. Ciresan, U. Meier, L. Gambardella, J. Schmidhuber
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
- 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
- 128.4K
- Training data
- 3,380,475 tokens
- Epochs
- 30
1st CNN layer: 20*4*4=320 2nd CNN layer: 20*40*9*9=64800 1st FC layer: 40*3*3*150=54000 2nd FC layer: 150*62=9300 Total : 320+64800+54000+9300=128420
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
- 2.6 × 10¹⁶ FLOP
- How it was established
- Operation counting,Hardware
GPU hour estimate: 30 epochs, 6 hours per network, 7 networks total 7*6*60*60*(2*1580000000000+2*1345000000000)*0.3=2.65e17 Counting estimate: 800000 training examples, 30 epochs 1st CNN layer: 2*20*26*26*4*4=432640 2nd CNN layer: 2*20*6*6*9*9*40=4665600 1st FC layer: 2*40*3*3*150=108000 2nd FC layer: 2*150*62=18600 Total: 432640+4665600+108000+18600=5224840 5224840*3*800000*30*7=2633319360000000=2.6e15 Geometric mean: sqrt(2.65e17*2.6e15)=2.6e16
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 GeForce GTX 580,NVIDIA GeForce GTX 480
- Chips used
- 4
- Wall-clock time
- 42 hours
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
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Convolutional Neural Network Committees for Handwritten Character Classification
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
CNN Committee (NIST) was published by IDSIA, in the country recorded as Switzerland, during September 2011. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of 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
Training it took a computation budget of roughly 2.6 × 10¹⁶ FLOP, on hardware recorded as NVIDIA GeForce GTX 580,NVIDIA GeForce GTX 480. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 3,380,475 tokens of text.
It is tracked in the underlying dataset for one reason in particular: historical significance.
Answers
CNN Committee (NIST) — common questions
CNN Committee (NIST)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
CNN Committee (NIST)— how many parameters does it have?
It has a parameter count of 128.4K. 1st CNN layer: 20*4*4=320 2nd CNN layer: 20*40*9*9=64800 1st FC layer: 40*3*3*150=54000 2nd FC layer: 150*62=9300 Total : 320+64800+54000+9300=128420. 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.
CNN Committee (NIST)— who created it?
It was published by IDSIA, based in Switzerland, an organisation categorised as academia.
CNN Committee (NIST)— when was it released?
It was published in September 2011. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
CNN Committee (NIST)— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
CNN Committee (NIST)— how much compute was used to train it?
Training consumed around 2.6 × 10¹⁶ FLOP, on hardware recorded as NVIDIA GeForce GTX 580,NVIDIA GeForce GTX 480. 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.
CNN Committee (NIST)— 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.
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.