LISSOM

Closed weights University of Texas at Austin 432.8K parameters November 1995

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
University of Texas at Austin
Organisation type
Academia
Country
United States of America
Published
27 November 1995
Authors
Yoonsuck Choe, Joseph Sirosh, R. Miikkulainen

What it does

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

Domain
Vision
Task
Digit 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
432.8K

Total connections 32*32*20*20+20*20*48+20*20*10=432800 Input: 32*32, Lissom: 20*20, Output: 10 (Figure 1a), up to 48 lateral connections per Lissom neuron (Figure 1b)

Training data
2,000 tokens

"LISSOM was trained with 2000 patterns"

Epochs
38

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 × 10¹¹ FLOP

Lissom connections: 32*32*20*20+20*20*48=428800 Lissom compute: 2*428800*3*38*2000=195532800000=1.96e11 Perceptron connections: 20*20*10=4000 Perceptron compute: 2*4000*3*500*1700=20400000000=2e10 Total compute: 195532800000+12000000=195544800000=1.96e11 "LISSOM was trained with 2000 patterns" "The initial self-organizing map was formed in 8 epochs over the training set, gradually reducing the neighborhood radius from 20 to 8. The lateral connections were then added to the system, and over anoth…

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
SOTA improvement,Historical significance

"The recognition rate on a subset of NIST database 3 is 4.0% higher with LISSOM than with a regular Self-Organizing Map (SOM) as the front end, and 15.8% higher than recognition of raw input bitmaps directly. "

Record confidence
Likely

Sources

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

Reference
Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition
Last updated
28 November 2025

What the numbers mean

Background

LISSOM was published by University of Texas at Austin, in United States of America, in November 1995. The organisation is categorised as academia.

It works in Vision, and is recorded as doing digit 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

The training run consumed about 2 × 10¹¹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 2,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement,Historical significance.

Answers

LISSOM — common questions

01

How much compute was used to train LISSOM?

Around 2 × 10¹¹ 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 LISSOM?

None. LISSOM 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 LISSOM open source?

The licensing for LISSOM 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 LISSOM have?

LISSOM has 432.8K parameters. Total connections 32*32*20*20+20*20*48+20*20*10=432800 Input: 32*32, Lissom: 20*20, Output: 10 (Figure 1a), up to 48 lateral connections per Lissom neuron (Figure 1b). 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

Who created LISSOM?

LISSOM was published by University of Texas at Austin, based in United States of America, categorised as academia.

06

When was LISSOM released?

LISSOM was published in November 1995. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is LISSOM used for?

LISSOM works in Vision, and is recorded as handling digit 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.

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.