Sparse Vision Encoding

Closed weights Stanford University November 2006

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
Organisation type
Academia
Country
United States of America
Published
1 November 2006
Authors
Honglak Lee, Alexis Battle, Rajat Raina, Andrew Y. Ng

What it does

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

Domain
Vision
Task
Image classification
Approach
Unsupervised

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.

Training data
tokens

However, these are 1000 20x20 pixel "bases", not images

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
9.6 × 10¹² FLOP

(Just for natural images) "All experiments were conducted on a Linux machine with AMD Opteron 2GHz CPU and 2GB RAM. ... For example, we were able to learn a set of 1,024 bases (each 14×14 pixels)in about 2 hours and a set of 2,000 bases (each 20×20 pixels) in about 10 hours." I filtered for 2GHz Opteron models that came out in 2005, of which there are five: https://www.techpowerup.com/cpu-specs/?mfgr=AMD&released=2005&generation=AMD%20Opteron&sort=name Found a source which indicates 3 cycles …

How it was established
Hardware

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
10 hours

"...in about 2 hours and a set of 2,000 bases (each 20×20 pixels) in about 10 hours."

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
3,512

Sources

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

Reference
Efficient sparse coding algorithms
Last updated
28 November 2025

What the numbers mean

Background

Sparse Vision Encoding was published by Stanford University, in the country recorded as United States of America, during November 2006. The publishing organisation is categorised as academia.

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

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

Producing it required arithmetic totalling around 9.6 × 10¹² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Sparse Vision Encoding — common questions

01

Sparse Vision Encoding— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

02

Sparse Vision Encoding— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

03

Sparse Vision Encoding— who created it?

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

04

Sparse Vision Encoding— when was it released?

It was published in November 2006. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

Sparse Vision Encoding— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

Sparse Vision Encoding— how much compute was used to train it?

Training consumed around 9.6 × 10¹² 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.

07

Sparse Vision Encoding— 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.