Translation-invariant MLP

Closed weights Carnegie Mellon University (CMU) 0.8K parameters June 1987

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
Carnegie Mellon University (CMU)
Organisation type
Academia
Country
United States of America
Published
15 June 1987
Authors
Geoffrey E. Hinton

What it does

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

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
0.8K

Network: 12-60-6-16 Weights: 6*60+60*6+6*16=816 Layer 2 was only sparsely connected to input layer

Training data
160 tokens
Epochs
23,020

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
1.8 × 10¹⁰ FLOP

FLOPs: 2*816*3*160*23020=18032947200=1.8e10

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.

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
Learning Translation Invariant Recognition in a Massively Parallel Network
Last updated
28 November 2025

What the numbers mean

Background

Translation-invariant MLP was published by Carnegie Mellon University (CMU), in United States of America, in June 1987. academia is the category the publisher falls under.

and is recorded as doing object recognition.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Producing it required around 1.8 × 10¹⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 160 tokens.

The reason it appears in this catalogue at all is historical significance.

Answers

Translation-invariant MLP — common questions

01

How many parameters does Translation-invariant MLP have?

Translation-invariant MLP has 0.8K parameters. Network: 12-60-6-16 Weights: 6*60+60*6+6*16=816 Layer 2 was only sparsely connected to input layer. 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.

02

Who created Translation-invariant MLP?

Translation-invariant MLP was published by Carnegie Mellon University (CMU), based in United States of America, categorised as academia.

03

When was Translation-invariant MLP released?

Translation-invariant MLP was published in June 1987. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is Translation-invariant MLP used for?

and is recorded as handling object recognition. 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.

05

How much compute was used to train Translation-invariant MLP?

Around 1.8 × 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.

06

What GPU do I need to run Translation-invariant MLP?

None. Translation-invariant MLP 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.

07

Is Translation-invariant MLP open source?

The licensing for Translation-invariant MLP was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

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.