Dropout (MNIST)

Closed weights University of Toronto 5.6M parameters June 2012

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 Toronto
Organisation type
Academia
Country
Canada
Published
3 June 2012
Authors
GE Hinton, N Srivastava, A Krizhevsky

What it does

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

Domain
Vision
Task
Character recognition (OCR)

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
5.6M

We show results for 4 nets (784-800-800-10, 784-1200-1200-10, 784-2000-2000-10, 784-1200-1200-1200-10) 784*2000+2000*2000+10*2000+6010=5594010

Training data
60,000 tokens

The MNIST database contains 60,000 training images and 10,000 testing images (Wikipedia)

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
6 × 10¹⁵ FLOP

Num mul-add / forward pass 2 FLOPs / mult-add 3 total mult-add / fp mult-add 3000 epochs 60000 training samples

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.

Training hardware
NVIDIA GeForce GTX 580

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
Training code
Open (non-commercial)

http://www.cs.toronto.edu/~nitish/dropout see model files

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
Highly cited
Record confidence
Confident
Citations
7,999

Sources

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

Reference
Improving neural networks by preventing co-adaptation of feature detectors
Last updated
25 May 2026

What the numbers mean

Where it came from

Dropout (MNIST) was published by University of Toronto, in Canada, in June 2012. It comes out of academia.

It works in Vision, and is recorded as doing character recognition (OCR).

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

How it was trained

The training run consumed about 6 × 10¹⁵ FLOP, on NVIDIA GeForce GTX 580. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 60,000 tokens.

The reason it appears in this catalogue at all is highly cited.

Answers

Dropout (MNIST) — common questions

01

How much compute was used to train Dropout (MNIST)?

Around 6 × 10¹⁵ FLOP, on NVIDIA GeForce GTX 580. 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 Dropout (MNIST)?

None. Dropout (MNIST) 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 Dropout (MNIST) open source?

No. Dropout (MNIST) has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does Dropout (MNIST) have?

Dropout (MNIST) has 5.6M parameters. We show results for 4 nets (784-800-800-10, 784-1200-1200-10, 784-2000-2000-10, 784-1200-1200-1200-10) 784*2000+2000*2000+10*2000+6010=5594010. 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 Dropout (MNIST)?

Dropout (MNIST) was published by University of Toronto, based in Canada, categorised as academia.

06

When was Dropout (MNIST) released?

Dropout (MNIST) was published in June 2012. 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 Dropout (MNIST) used for?

Dropout (MNIST) works in Vision, and is recorded as handling character recognition (OCR). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Source

Original publication

Record last updated 25 May 2026

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.