concept
active
concept:structure-in-representationsStructure in representations
The central question of whether representational geometry implies corresponding computational structure
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Structure in computationassociated_withThe actual computational operations a model performs, which the paper argues need not mirror representational 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.
- The central research question motivating the paper
- How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.
- Conventional programming constructs like variables, arrays; claimed unnecessary for Elephant programs.
- Hierarchical representations in neural networks that allow compression and coordinated behaviour while retaining sensitivity to input changes.
- The aspect of design dealing with data structures, modules, and implementation.
- Representations of one's own mental states; associated with consciousness in higher-order theories.
- Dominant interpretation of generative models as neural structures with representational content; main target of critique
- The distribution of latent representations produced by the model under unperturbed inputs