question
active
question:will-learning-independent-subcomponents-yield-as-short-a-description-of-the-network-s-function-as-possibleWill learning independent subcomponents yield as short a description of the network's function as possible?
Open issue.
Source paper
extracted_from(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey
Neighborhood — ranked by edge-count
Papers (1)
paper
- Stochastic Parameter Decompositionassociated_withmentions
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.
- Universality hypothesis to be tested across families.
- Central thesis enabling unification of neural, developmental, ecological, and social networks as instances of collective intelligence.
- Central claim from connectionist models: complex coordination emerges without centralized control or external teacher.
- Clarifies what unsupervised learning does.
- Frequency alone is insufficient to predict learning order; both frequency and complexity are neededclaim0.734From complexity sweeps.
- Recent models show GRNs can perform associative learning and pattern completion.
- Motivated by the finding that lexical entailment decomposes into word identities.