ANN Eye Tracker

Closed weights 5.6K parameters November 1993

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
29 November 1993
Authors
S. Baluja, D. Pomerleau

What it does

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

Domain
Vision
Task
Miscellaneous image analysis
Approach
Supervised

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
5.6K

15*15*20+20+50*10*2+100=5620 Hidden layer is split, 15*15 image input, 2*50 output neurons (see Figure 2) Hidden size up to 20 neurons ("This architecture was used with varying numbers of hidden units in the single, divided, hidden layer; experiments with 10, 16 and 20 hidden units were performed. ")

Training data
4,000 tokens
Epochs
260

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

2*5620*3*520000=17534400000 Training examples: 2000*260=520000 "As mentioned before, 2000 image/position pairs were gathered for training" "All of the networks described in this paper are trained with the same parameters for 260 epochs"

How it was established
Operation counting

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
1 hours

"Training the 8x2 hidden layer network using the 15x40 input retina, with 2000 images, takes approximately 30-40 minutes on a Sun SPARC 10 machine. "

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
Confident

Sources

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

Reference
Non-Intrusive Gaze Tracking Using Artificial Neural Networks
Last updated
28 November 2025

What the numbers mean

About this model

ANN Eye Tracker was published by its authors, during November 1993.

It works in the domain of Vision, and is recorded as performing the task of miscellaneous image analysis.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

Training it took a computation budget of roughly 1.8 × 10¹⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 4,000 tokens of text.

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

Answers

ANN Eye Tracker — common questions

01

ANN Eye Tracker— 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

ANN Eye Tracker— how many parameters does it have?

It has a parameter count of 5.6K. 15*15*20+20+50*10*2+100=5620 Hidden layer is split, 15*15 image input, 2*50 output neurons (see Figure 2) Hidden size up to 20 neurons ("This architecture was used with varying numbers of hidden units in the single, divided, hidden layer; experiments with 10, 16 and 20 hidden units were performed. "). 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.

03

ANN Eye Tracker— when was it released?

It was published in November 1993. 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

ANN Eye Tracker— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of miscellaneous image analysis. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

ANN Eye Tracker— how much compute was used to train it?

Training consumed 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

ANN Eye Tracker— 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.