What if the FFN is a graph?
An open question about the structure inside a model.
Could a feed-forward network be usefully treated as an addressable graph? This question connects model representation to traversal and querying, without claiming an experimental answer.
What if the FFN is a graph?
The question is about whether the representation makes something useful possible: addressing, traversing or explaining the computation.
THE THREAD
Start with the representation. Ask what can be addressed. Specify a traversal, then compare it with the original computation. Keep the distinction between an explanatory picture and an operational result.
AN ANSWER IS STILL OPEN
Question: addressable structure
Required: reproducible experiments and explicit baselines
A compelling representation must still earn its result.
an answer is still open — question: addressable structure; required: reproducible experiments and explicit baselines. A compelling representation must still earn its result.
SOURCES & PROVENANCE
- Homepage production brief
Open research question supplied by Chris Hay.
AUTHOR / CHRIS HAY · VERSION / 0.1
REFERENCE THIS DRAFT
An unpublished working record. These references identify the draft and omit a publication date. They become version-specific publication citations when the record is released.
Chris Hay. What if the FFN is a graph? [Unpublished draft, version 0.1]. https://chrishayuk.com/research/ffn-as-graph