finding
active
finding:neuron-contributions-of-spd-subcomponents-closely-match-target-model-across-all-100-featuresNeuron contributions of SPD subcomponents closely match target model across all 100 features
Figure 7.
Source paper
extracted_from(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Author interpretation.
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.
- Figure 10 discrepancy.
- SPD splits W_out into 50 subcomponents forming a single rank-50 component in compressed computation modelfinding0.800Contradicts APD's 100 components for W_out.
- Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.
- SPD finds 100 W_in components and a single rank-50 W_out component spanning both layers in the 2-layer modelfinding0.783Multi-layer mechanisms.
- SPD decomposes W_in of compressed computation model into 100 subcomponents, one per input featurefinding0.782Neuron contributions match target.
- Data-induced competition over resources.
- Fundamental theoretical claim motivating DAS, attributed to Smolensky/Rumelhart/McClelland.
- Primary empirical claim of the paper