Learning past tenses
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
- Stanford University
- Organisation type
- Academia
- Country
- United States of America
- Published
- 3 January 1986
- Authors
- Rumelhart, D. E., & McClelland, J. L
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Verb conjugation
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
- 211.6K
- Training data
- tokens
Source: https://files.eric.ed.gov/fulltext/ED267419.pdf p.9: network architecture is given, with two layers of hidden units. The hidden units are called “Wickelfeature representation”. The “modifiable connections” are only between the hidden units. p.19: “All in all then, we used only 460 of the 1,210 possible Wickelfeatures. Using this representation, a verb is represented by a pattern of activation over a set of 460 Wickelfeature units."
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 318
Sources
Where this record came from and when it was last checked.
- Reference
- Learning the past tenses of English verbs: Implicit rules or parallel distributed processing?
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Learning past tenses was published by Stanford University, in the country recorded as United States of America, during January 1986. The category the publisher falls under is academia.
It works in the domain of Language, and is recorded as performing the task of verb conjugation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
Learning past tenses — common questions
Learning past tenses— how many parameters does it have?
It has a parameter count of 211.6K. Source: https://files.eric.ed.gov/fulltext/ED267419.pdf p.9: network architecture is given, with two layers of hidden units. The hidden units are called “Wickelfeature representation”. The “modifiable connections” are only between the hidden units. p.19: “All in all then, we used only 460 of the 1,210 possible Wickelfeatures. Using this representation, a verb is represented by a pattern of activation over a set of 460 Wickelfeature units.". 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.
Learning past tenses— who created it?
It was published by Stanford University, based in United States of America, an organisation categorised as academia.
Learning past tenses— when was it released?
It was published in January 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.
Learning past tenses— what is it used for?
It works in the domain of Language, and is recorded as handling the task of verb conjugation. 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.
Learning past tenses— 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.
Learning past tenses— 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.
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.