Pooling CNN (NORB)

Closed weights University of Bonn 268.7K parameters September 2010

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 Bonn
Organisation type
Academia
Country
Germany
Published
15 September 2010
Authors
Dominik Scherer, Andreas C. Müller, Sven Behnke

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
268.7K

Figure 1 C1: 2*16*5*5=800 C3: 16*64*6*6=36864 F5: 64*6*6*100=230400 F6: 100*6=600 Total: 800+36864+230400+600=268664

Training data
24,300 tokens

Each pattern consists of a binocular pair of 96 × 96 grayscale images, with a total of 24,300 training patterns and the same amount of testing patterns.

Epochs
1,000

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
1.5 × 10¹⁵ FLOP

Forward FLOP C1: 2*2*16*5*5*92*92=13542400 C3: 2*16*16*6*6*18*18=5971968 F5: 2*64*6*6*100=460800 F6: 2*100*6=1200 Total: 13542400+5971968+460800+1200=19976368 1000 epochs, 24300 training examples 19976368*3*24300*1000=1456277227200000=1.5e15

How it was established
Operation counting

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

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,Highly cited,SOTA improvement

"we achieve state-of-the-art error rates of 4.57% on the NORB normalized-uniform dataset and 5.6% on the NORB jittered-cluttered dataset."

Record confidence
Confident

Sources

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

Reference
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Last updated
11 February 2026

What the numbers mean

What this model is

Pooling CNN (NORB) was published by University of Bonn, in the country recorded as Germany, during September 2010. It comes out of an organisation categorised as 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

Producing it required arithmetic totalling around 1.5 × 10¹⁵ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 24,300 tokens of text.

Its inclusion criterion: historical significance,Highly cited,SOTA improvement.

Answers

Pooling CNN (NORB) — common questions

01

Pooling CNN (NORB)— 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.

02

Pooling CNN (NORB)— how much compute was used to train it?

Training consumed around 1.5 × 10¹⁵ 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.

03

Pooling CNN (NORB)— 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.

04

Pooling CNN (NORB)— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

05

Pooling CNN (NORB)— how many parameters does it have?

It has a parameter count of 268.7K. Figure 1 C1: 2*16*5*5=800 C3: 16*64*6*6=36864 F5: 64*6*6*100=230400 F6: 100*6=600 Total: 800+36864+230400+600=268664. 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.

06

Pooling CNN (NORB)— who created it?

It was published by University of Bonn, based in Germany, an organisation categorised as academia.

07

Pooling CNN (NORB)— when was it released?

It was published in September 2010. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 11 February 2026

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.