MLP with back-propagation
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 California San Diego,Carnegie Mellon University (CMU)
- Organisation type
- Academia,Academia
- Country
- United States of America
- Published
- 1 October 1986
- Authors
- Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Mathematics
- Task
- Triplet completion
- 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.
- Parameters
- 0.7K
- Training data
- 104 tokens
Architecture in Figure 3: 24+12 input -> 6 + 6 hidden -> 12 hidden -> 6 hidden -> 24 output Parameters: 6*24+6*12+12*12+6*12+24*12=720
There are 104 relationship triplets ("[...] of the 104 possible triplets")
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
- 6.7 × 10⁸ FLOP
- How it was established
- Operation counting
We assume that the number of mult-adds per pass is equal to the number of parameters -> 2*720=1440 FLOP per forward pass. "We trained the network for 1500 sweeps" There are 104 relationship triplets ("[...] of the 104 possible triplets") FLOP: 1500*104*3*1440=673920000
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
- Highly cited
- Record confidence
- Confident
- Citations
- 29,621
Sources
Where this record came from and when it was last checked.
- Reference
- Learning representations by back-propagating errors
- Last updated
- 1 January 2026
What the numbers mean
Background
MLP with back-propagation was published by University of California San Diego,Carnegie Mellon University (CMU), in United States of America, in October 1986. The organisation is categorised as academia,Academia.
It works in Mathematics, and is recorded as doing triplet completion.
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 roughly 6.7 × 10⁸ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 104 tokens of text.
It is tracked in the underlying dataset for one reason in particular: highly cited.
Answers
MLP with back-propagation — common questions
Is MLP with back-propagation open source?
The licensing for MLP with back-propagation 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 MLP with back-propagation have?
MLP with back-propagation has 0.7K parameters. Architecture in Figure 3: 24+12 input -> 6 + 6 hidden -> 12 hidden -> 6 hidden -> 24 output Parameters: 6*24+6*12+12*12+6*12+24*12=720. 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.
Who created MLP with back-propagation?
MLP with back-propagation was published by University of California San Diego,Carnegie Mellon University (CMU), based in United States of America, categorised as academia,Academia.
When was MLP with back-propagation released?
MLP with back-propagation was published in October 1986. 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 MLP with back-propagation used for?
MLP with back-propagation works in Mathematics, and is recorded as handling triplet completion. 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.
How much compute was used to train MLP with back-propagation?
Around 6.7 × 10⁸ 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 MLP with back-propagation?
None. MLP with back-propagation 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.
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.