Reference collection
Published machine-learning models
Models published for others to use, held as records — so one can be found by what it is for rather than by what it is called.
What’s on this shelf
Filed beside the repository and research collections, so a model and the work it came out of sit within reach of each other.
What one record is
One published model, filed as a record rather than as a page describing it.
Every record also keeps the address it was read from, so any answer built on it can be followed back to the original.
What you can do with it
What this collection is kept for.
Find one by what it does
Describe the task in plain words. Model names carry almost no information about their purpose, which is exactly the problem.
Read it beside the research
Repositories and papers are on neighbouring shelves, so a model and the work behind it turn up in one search.
Follow it back
Every record keeps the address it was read from, so a model can be checked where it was published.
What it is not good for
known limits- It is not a benchmark table. Nothing here ranks models or tells you which one is better at your task.
- It is not a download or a hosting service. The record says a model was published; running it is somewhere else entirely.
Where it’s used
Code
The Code workspace reads this collection when the question is which model exists for a job, not how to write one.
Read, filed and kept current.
This collection is one shelf of the askFinz index — material read from the source and filed as the kind of thing it is, rather than as undifferentiated web pages. The counts above are read from the running system.