concept
active
concept:distributed-neural-representations

Distributed Neural Representations

Representations where individual neurons play multiple conceptual roles; patterns consisting of linear combinations of unit vectors.

Neighborhood — ranked by edge-count

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
  • Key insight that rotating a neural representation to a non-standard basis can reveal distributed causal structure invisible in standard neuron-aligned basis.
  • Prior assumption that high-level variables align with disjoint groups of neurons in standard basis; contrasted with distributed representations.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.