Stacked Semisuperviser Autoencoders
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
- New York University (NYU),Microsoft
- Organisation type
- Academia,Industry
- Country
- United States of America
- Published
- 15 July 2008
- Authors
- MA Ranzato, M Szummer
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Document representation
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
- 3M
- Training data
- tokens
"The 20 Newsgroups dataset contains 18845 postings taken from the Usenet newsgroup collection. Documents are partitioned into 20 topics. The dataset is split into 11314 training documents and 7531 test documents. Training and test articles are separated in time. Reuters has a predefined ModApte split of the data into 11413 training documents and 4024 test doc- uments. Documents belong to one of 91 topics. The Ohsumed dataset has 34389 documents with 30689 words and each document might be assigne…
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 243
Sources
Where this record came from and when it was last checked.
- Reference
- Semisupervised learning of compact document representations with deep networks
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Stacked Semisuperviser Autoencoders was published by New York University (NYU),Microsoft, in United States of America, in July 2008. The organisation is categorised as academia,Industry.
It works in Language, and is recorded as doing document representation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
Stacked Semisuperviser Autoencoders — common questions
What GPU do I need to run Stacked Semisuperviser Autoencoders?
None. Stacked Semisuperviser Autoencoders 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 Stacked Semisuperviser Autoencoders open source?
The licensing for Stacked Semisuperviser Autoencoders 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 Stacked Semisuperviser Autoencoders have?
Stacked Semisuperviser Autoencoders has 3M parameters. 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 Stacked Semisuperviser Autoencoders?
Stacked Semisuperviser Autoencoders was published by New York University (NYU),Microsoft, based in United States of America, categorised as academia,Industry.
When was Stacked Semisuperviser Autoencoders released?
Stacked Semisuperviser Autoencoders was published in July 2008. 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 Stacked Semisuperviser Autoencoders used for?
Stacked Semisuperviser Autoencoders works in Language, and is recorded as handling document representation. 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.
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.