Feedforward NN
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 Montreal / Université de Montréal
- Organisation type
- Academia
- Country
- Canada
- Published
- 13 May 2010
- Authors
- X Glorot, Y Bengio
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
- 7.1M
- Training data
- 90,000 tokens
pg250 of the paper, section 2.3: "We optimized feedforward neural networks with one to five hidden layers, with one thousand hidden units per layer" Input is a flattened 32x32 image, which corresponds to an input vector of length 3072 Output is a number from 0-9, so 10 neurons No. of params: 3072*1000 + 4*1000*1000 + 1000*10 = 7,082,000
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
- 3.5 × 10¹⁴ FLOP
- How it was established
- Operation counting
Roughly two times the number of parameters for ops per forward pass. So 2*7082000 params*3.5*140 epochs * 50k training images = 3.5e14
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
- 18,606
Sources
Where this record came from and when it was last checked.
- Reference
- Understanding the difficulty of training deep feedforward neural networks
- Last updated
- 1 January 2026
What the numbers mean
Background
Feedforward NN was published by University of Montreal / Université de Montréal, in the country recorded as Canada, during May 2010. It comes out of an organisation categorised as academia.
It works in the domain of Vision, and is recorded as performing the task of digit recognition.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Training it took a computation budget of roughly 3.5 × 10¹⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 90,000 tokens of text.
The reason it appears in this catalogue at all: highly cited.
Answers
Feedforward NN — common questions
Feedforward NN— 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.
Feedforward NN— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
Feedforward NN— how many parameters does it have?
It has a parameter count of 7.1M. pg250 of the paper, section 2.3: "We optimized feedforward neural networks with one to five hidden layers, with one thousand hidden units per layer" Input is a flattened 32x32 image, which corresponds to an input vector of length 3072 Output is a number from 0-9, so 10 neurons No. of params: 3072*1000 + 4*1000*1000 + 1000*10 = 7,082,000. 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.
Feedforward NN— who created it?
It was published by University of Montreal / Université de Montréal, based in Canada, an organisation categorised as academia.
Feedforward NN— when was it released?
It was published in May 2010. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Feedforward NN— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of 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.
Feedforward NN— how much compute was used to train it?
Training consumed around 3.5 × 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.
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.