Invariant image recognition

Closed weights Complutense University of Madrid June 1989

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
Complutense University of Madrid
Organisation type
Academia
Country
Spain
Published
18 June 1989
Authors
V. Cruz, G. Cristóbal, T. Michaux, S. Barquin

What it does

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

Domain
Vision
Task
Representation learning

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.

Training data
tokens

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
2.7 × 10¹⁰ FLOP

0.5*6*60*60*2.5e6 = 27000000000 = 2.7e10 Trained for 6h on a SUN-4 (section 4) Assumed utilization of 0.5 SUN-4 is estimated at 2.5e6 FLOP/s (Nordhaus, 2007)

How it was established
Hardware

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
6 hours

Section 4

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Frontier model
Yes
Why it is tracked
Historical significance
Record confidence
Confident

Sources

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

Reference
Invariant image recognition using a multi-network neural model
Last updated
28 November 2025

What the numbers mean

What this model is

Invariant image recognition was published by Complutense University of Madrid, in the country recorded as Spain, during June 1989. The category the publisher falls under is academia.

It works in the domain of Vision, and is recorded as performing the task of representation learning.

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 2.7 × 10¹⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Its inclusion criterion: historical significance.

Answers

Invariant image recognition — common questions

01

Invariant image recognition— 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.

02

Invariant image recognition— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

03

Invariant image recognition— who created it?

It was published by Complutense University of Madrid, based in Spain, an organisation categorised as academia.

04

Invariant image recognition— when was it released?

It was published in June 1989. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

Invariant image recognition— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of representation learning. 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.

06

Invariant image recognition— how much compute was used to train it?

Training consumed around 2.7 × 10¹⁰ 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.

07

Invariant image recognition— 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.

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.