LMICA

Closed weights 4.1M parameters December 2004

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
1 December 2004
Authors
Yoshitatsu Matsuda, K. Yamaguchi

What it does

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

Domain
Vision
Task
Object detection

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
4.1M

64*64*1000=4096000 "100000 samples of natural scenes of 64 × 64 pixels were given as X" "LMICA was carried out in 1000 layers"

Training data
100,000 tokens

"100000 samples of natural scenes of 64 × 64 pixels were given as X"

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
2.8 × 10¹⁵ FLOP

69*60*60*8*2800000000*0.5=2782080000000000=2.78e15 "it consumed about 69 hours with Intel 2.8GHz CPU" - Assuming they used an Intel Pentium 4 processor with 8 FLOP/cycle (https://en.wikipedia.org/wiki/FLOPS)

How it was established
Hardware

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
Training cost,Historical significance
Record confidence
Confident

Sources

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

Reference
Linear Multilayer Independent Component Analysis for Large Natural Scenes
Last updated
28 November 2025

What the numbers mean

About this model

LMICA was published by its authors, in December 2004.

It works in Vision, and is recorded as doing object detection.

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

What went into building it

Training it took roughly 2.8 × 10¹⁵ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Around 100,000 tokens went into training it.

The reason it appears in this catalogue at all is training cost,Historical significance.

Answers

LMICA — common questions

01

How much compute was used to train LMICA?

Around 2.8 × 10¹⁵ 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.

02

What GPU do I need to run LMICA?

None. LMICA 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.

03

Is LMICA open source?

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

04

How many parameters does LMICA have?

LMICA has 4.1M parameters. 64*64*1000=4096000 "100000 samples of natural scenes of 64 × 64 pixels were given as X" "LMICA was carried out in 1000 layers". 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.

05

When was LMICA released?

LMICA was published in December 2004. 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

What is LMICA used for?

LMICA works in Vision, and is recorded as handling object detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.