Siamese-TDNN
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
- Bell Laboratories
- Organisation type
- Industry
- Country
- United States of America
- Published
- 1 August 1993
- Authors
- J. Bromley, James W. Bentz, L. Bottou, Isabelle M Guyon, Yann LeCun, C. Moore, Eduard Säckinger, Roopak Shah
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
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
- 0.7K
- Training data
- 7,701 tokens
- Epochs
- 69
"The input is 8 by 200 units, the first convolutional layer is 6 by 192 units with each unit's receptive field covering 8 by 9 units of the input. The first averaging layer is 6 by 64 units, the second convolution layer is 4 by 57 with 6 by 8 receptive fields and the second averaging layer is 4 by 19" "Two separate sub-networks based on Time Delay Neural Networks (Lang and Hinton, 1988, Guyon et al. 1990) act on each input pattern to extract features," "All weights could be learnt, but the two s…
"We used up to 7,701 signature pairs"
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
- 1.3 × 10¹³ FLOP
- How it was established
- Operation counting
8073216*3*7701*69=12869570138112=1.29e13 Forward pass flop: 2*(2*200*200*8*6+2*64*64*6*4)=8073216 "We used up to 7,701 signature pairs" Epochs: 69 (Table 1)
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,Highly cited
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Signature Verification using a "Siamese" Time Delay Neural Network
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Siamese-TDNN was published by Bell Laboratories, in United States of America, in August 1993. The organisation is categorised as industry.
It works in Vision, and is recorded as doing image classification.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
The training run consumed about 1.3 × 10¹³ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
It was trained on about 7,701 tokens of text.
The reason it appears in this catalogue at all is historical significance,Highly cited.
Answers
Siamese-TDNN — common questions
Who created Siamese-TDNN?
Siamese-TDNN was published by Bell Laboratories, based in United States of America, categorised as industry.
When was Siamese-TDNN released?
Siamese-TDNN was published in August 1993. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Siamese-TDNN used for?
Siamese-TDNN works in Vision, and is recorded as handling image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train Siamese-TDNN?
Around 1.3 × 10¹³ 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.
What GPU do I need to run Siamese-TDNN?
None. Siamese-TDNN 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.
Is Siamese-TDNN open source?
The licensing for Siamese-TDNN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Siamese-TDNN have?
Siamese-TDNN has 0.7K parameters. "The input is 8 by 200 units, the first convolutional layer is 6 by 192 units with each unit's receptive field covering 8 by 9 units of the input. The first averaging layer is 6 by 64 units, the second convolution layer is 4 by 57 with 6 by 8 receptive fields and the second averaging layer is 4 by 19" "Two separate sub-networks based on Time Delay Neural Networks (Lang and Hinton, 1988, Guyon et al. 1990) act on each input pattern to extract features," "All weights could be learnt, but the two sub-networks were constrained to have identical weights." L1: H=1, W=200, C=8, K=9, D=6 L2: H=1, W=64, C=6, K=8, D=4 Parameters: 7*9*8+5*8*6=744. 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.
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.