concept
active
concept:structured-datastructured data
Training data with inherent geometric or relational structure, which induces geometric organization in model internals.
Neighborhood — ranked by edge-count
Claims (2)
claim
- Core claim of the paper: the right level of description for neural representations is geometric structure mirroring the world.
- Mechanistic explanation: geometric structure emerges naturally from standard training on data with underlying structure.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Conventional programming constructs like variables, arrays; claimed unnecessary for Elephant programs.
- The actual computational operations a model performs, which the paper argues need not mirror representational structure
- Question about the inner structure of the plenum, leading to the answer that it is pure unity without structure.
- Data structures stored as collections of tuples in tuple space, accessible to many processes.
- The central question of whether representational geometry implies corresponding computational structure
- Training environments formalized as graphs where nodes have sensory observations and edges represent actions; used to test structural generalization.
- Flusser’s category of complexity where the system elements have very complex internal relationships (like apparatus).
- A formal context with a suggestive interpretation used in conceptual scaling.