SVM-CNN

Closed weights New York University (NYU) 90.9K parameters June 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
New York University (NYU)
Organisation type
Academia
Country
United States of America
Published
17 June 2006
Authors
Fu Jie Huang, Yann LeCun

What it does

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

Domain
Vision
Task
Image classification
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
90.9K
Training data
583,200 tokens

To generate the training set, each image was perturbed with 10 different configurations of the above parameters, which makes up 291,600 image pairs of size 108×108. The testing set has 2 drawings of perturbations, and have

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
7.5 × 10¹⁴ FLOP

Training time: 5880+330=6210 minutes (Table 1) “The timing is normalized to hypothetical 1GHz single CPU.” Assuming utilization of 0.5 and AMD Athlon 64 Processor with 4 FLOP/cycle Compute: 6210*60*4*1000000000*0.5=745200000000000 = 7.4e14

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.

Chips used
1

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.

Frontier model
Yes
Why it is tracked
Historical significance
Record confidence
Confident

Sources

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

Reference
Large-scale Learning with SVM and Convolutional for Generic Object Categorization
Last updated
28 November 2025

What the numbers mean

What this model is

SVM-CNN was published by New York University (NYU), in the country recorded as United States of America, during June 2006. The category the publisher falls under is 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.

Training and provenance

Training it took a computation budget of roughly 7.5 × 10¹⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 583,200 tokens of text.

It is tracked in the underlying dataset for one reason in particular: historical significance.

Answers

SVM-CNN — common questions

01

SVM-CNN— who created it?

It was published by New York University (NYU), based in United States of America, an organisation categorised as academia.

02

SVM-CNN— when was it released?

It was published in June 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.

03

SVM-CNN— 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.

04

SVM-CNN— how much compute was used to train it?

Training consumed around 7.5 × 10¹⁴ 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.

05

SVM-CNN— 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.

06

SVM-CNN— is it open source?

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

07

SVM-CNN— how many parameters does it have?

It has a parameter count of 90.9K. 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.

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.