JPMAX

Closed weights 4.4K parameters December 1994

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.

Published
2 December 1994
Authors
Suzanna Becker

What it does

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

Domain
Vision
Task
Image representation

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
4.4K

Inputs are 12x12 pixels (Figure 3). They first train the architecture in Figure 2 a), then freeze it and train the additional layer in Figure 3 b). Figure 2 a): 2*(12*12*15) + 2*15 = 4,350 Figure 2 b): 2*(12*12*15) + 2*15 + 2*(15*3) + 2*3 = 4,446

Training data
1,500 tokens

“Figure 3: 10 of the 1500 training patterns”

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
8.1 × 10⁷ FLOP

Training 2a): "The learning took about 3000 iterations of steepest descent" Assuming each iteration refers to a single image. 6 * 4446 * 3000 = 80,028,000 Training 2b): "While keeping the first layer of weights frozen, this network was trained using exactly the same cost function as the first layer for about 30 iterations using a gradient-based learning method." 6 * 4446 * 30 = 800,280 Total: 80,828,280

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
Historical significance
Record confidence
Speculative

Sources

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

Reference
JPMAX: Learning to Recognize Moving Objects as a Model-fitting Problem
Last updated
28 November 2025

What the numbers mean

About this model

JPMAX was published by its authors, in December 1994.

It works in Vision, and is recorded as doing image representation.

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

How it was trained

The training run consumed about 8.1 × 10⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 1,500 tokens.

Its inclusion criterion is historical significance.

Answers

JPMAX — common questions

01

What is JPMAX used for?

JPMAX works in Vision, and is recorded as handling image representation. 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.

02

How much compute was used to train JPMAX?

Around 8.1 × 10⁷ 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.

03

What GPU do I need to run JPMAX?

None. JPMAX 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.

04

Is JPMAX open source?

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

05

How many parameters does JPMAX have?

JPMAX has 4.4K parameters. Inputs are 12x12 pixels (Figure 3). They first train the architecture in Figure 2 a), then freeze it and train the additional layer in Figure 3 b). Figure 2 a): 2*(12*12*15) + 2*15 = 4,350 Figure 2 b): 2*(12*12*15) + 2*15 + 2*(15*3) + 2*3 = 4,446. 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.

06

When was JPMAX released?

JPMAX was published in December 1994. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.