Invariant CNN

Closed weights New York University (NYU) 90.6K parameters June 2004

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
New York University (NYU)
Organisation type
Academia
Country
United States of America
Published
27 June 2004
Authors
Yann LeCun, Fu Jie Huang, L. Bottou

What it does

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

Domain
Vision
Task
Object recognition

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
90.6K

"The network has a total of 90,575 trainable parameters."

Training data
24,300 tokens

"normalized-uniform set: 5 classes, centered, unperturbed objects on uniform backgrounds. 24,300 training samples, 24,300 testing samples."

Epochs
10

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
9.7 × 10¹¹ FLOP

"A full propagation through the network requires 3,896,920 multiply-adds." - it's not entirely clear whether this refers to a forward pass or forward + backward pass (I assumed the latter) "We used a stochastic version of the Levenberg-Marquardt algorithm with diagonal approximation of the Hessian [7], for approximately 250,000 online updates." 3896920*250000=974230000000=9.7e11

How it was established
Operation counting

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,Historical significance
Record confidence
Confident

Sources

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

Reference
Learning methods for generic object recognition with invariance to pose and lighting
Last updated
28 November 2025

What the numbers mean

About this model

Invariant CNN was published by New York University (NYU), in the country recorded as United States of America, during June 2004. It comes out of an organisation categorised as academia.

It works in the domain of Vision, and is recorded as performing the task of object recognition.

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

Training and provenance

The training run consumed about 9.7 × 10¹¹ 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.

It is tracked in the underlying dataset for one reason in particular: highly cited,Historical significance.

Answers

Invariant CNN — common questions

01

Invariant CNN— 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.

02

Invariant CNN— 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.

03

Invariant CNN— how many parameters does it have?

It has a parameter count of 90.6K. "The network has a total of 90,575 trainable parameters.". 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.

04

Invariant CNN— who created it?

It was published by New York University (NYU), based in United States of America, an organisation categorised as academia.

05

Invariant CNN— when was it released?

It was published in June 2004. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

Invariant CNN— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of object recognition. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

Invariant CNN— how much compute was used to train it?

Training consumed around 9.7 × 10¹¹ 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.

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.