hypothesis
active
hypothesis:spd-scalability-will-enable-investigating-memorization-and-parameter-storage-capacitySPD scalability will enable investigating memorization and parameter storage capacity
Future direction.
Source paper
extracted_from(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central claim.
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.
- Discussion and App. A.
- SPD decomposes W_in of compressed computation model into 100 subcomponents, one per input featurefinding0.748Neuron contributions match target.
- Section 4.
- Supported by reported speedup through 64 nodes on iPSC/2.
- Processes scaling goals and stressors form positive feedback loop with modularity; both arise from and potentiate power of evolution, enabling specific predictions for cognitive capacity scaling.
- SPD splits W_out into 50 subcomponents forming a single rank-50 component in compressed computation modelfinding0.733Contradicts APD's 100 components for W_out.
- Open problem.
- Quantitative comparison supporting SAE utility.