Innervator

Closed weights Stanford University,California Institute of Technology 0K parameters December 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
Stanford University,California Institute of Technology
Organisation type
Academia,Academia
Country
United States of America
Published
1 December 1989
Authors
Geoffrey Miller, Peter Todd, and Shailesh Hegde

What it does

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

Domain
Mathematics
Task
Pattern classification

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
0K

Each net has 5 units

Training data
10,240 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
1.2 × 10⁸ FLOP

10 params * 6 FLOP/param/pass * 4 datapoints * 1000 epochs * 50 individuals * 10 generations

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.

Record confidence
Confident
Citations
1,132

Sources

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

Reference
Designing neural networks using genetic algorithms
Last updated
28 November 2025

What the numbers mean

Where it came from

Innervator was published by Stanford University,California Institute of Technology, in the country recorded as United States of America, during December 1989. The category the publisher falls under is academia,Academia.

It works in the domain of Mathematics, and is recorded as performing the task of pattern 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 1.2 × 10⁸ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 10,240 tokens of text.

Answers

Innervator — common questions

01

Innervator— 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

Innervator— 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

Innervator— how many parameters does it have?

It has a parameter count of 0K. Each net has 5 units. 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

Innervator— who created it?

It was published by Stanford University,California Institute of Technology, based in United States of America, an organisation categorised as academia,Academia.

05

Innervator— when was it released?

It was published in December 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.

06

Innervator— what is it used for?

It works in the domain of Mathematics, and is recorded as handling the task of pattern classification. 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.

07

Innervator— how much compute was used to train it?

Training consumed around 1.2 × 10⁸ 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.