concept
active
concept:distributed-neural-representationsDistributed Neural Representations
Representations where individual neurons play multiple conceptual roles; patterns consisting of linear combinations of unit vectors.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- The theoretical framework from Rumelhart, McClelland, and Smolensky (1986) identifying distributed representations in neural networks; theoretical precursor to DAS.
Methods (1)
method
- The core method introduced in this paper: finds alignments between high-level causal variables and distributed neural representations via gradient descent.
Concepts (2)
concept
- Change-of-Basis for Neural Representationsassociated_withKey insight that rotating a neural representation to a non-standard basis can reveal distributed causal structure invisible in standard neuron-aligned basis.
- Localist RepresentationscontradictsPrior assumption that high-level variables align with disjoint groups of neurons in standard basis; contrasted with distributed representations.
Quotes (1)
quote
- Load-bearing theoretical claim providing the conceptual foundation for DAS.
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.
- Idea that information is spread across many neurons; superposition is a subtype.
- The broader conceptual framework that neural activations exhibit non-Euclidean geometric structure causally linked to behavior.
- Cognitive process spread across human and non-human agents; a goal of Pask’s and Friedman’s cybernetic diagrams.
- Neural Representations of Location Composed of Spatially Periodic Bands (Krupic et al., 2012)concept0.788Discovery of band cells; TEM-t also recapitulates these representations.
- The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
- Cognition in nervous systems, used as a modelling target