Invariant image recognition
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
- How it was established
- Hardware
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)
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 Spain, in June 1989. academia is the category the publisher falls under.
It works in Vision, and is recorded as doing 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 describes the cost of creating it and has no bearing on how quickly it generates text.
Its inclusion criterion is historical significance.
Answers
Invariant image recognition — common questions
Is Invariant image recognition open source?
The licensing for Invariant image recognition was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Invariant image recognition have?
No parameter count has been published for Invariant image recognition, which is why no memory or speed figure appears on this page.
Who created Invariant image recognition?
Invariant image recognition was published by Complutense University of Madrid, based in Spain, categorised as academia.
When was Invariant image recognition released?
Invariant image recognition 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.
What is Invariant image recognition used for?
Invariant image recognition works in Vision, and is recorded as handling 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.
How much compute was used to train Invariant image recognition?
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.
What GPU do I need to run Invariant image recognition?
None. Invariant image recognition 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.