method
active
method:balancedsubnet-bsnBalancedSubnet (BSN)
Supervised unlearning baseline using a binary mask trained on forget/retain sets.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Deep architecture with recurrent connections within layers, can learn compressed representations and retain stable attractors.
- B10 fine-tuning yields smallest OOD drops when transferring to other bases
- Average of per-layer S(ℓ) scores, summarizing the breadth of anchoring trajectory.
- Ancient mechanism using ion channels, gap junctions, and neurotransmitters as 'cognitive glue' enabling collective intelligence across morphogenesis and behavior.
- Bijective invertible architecture used to implement non-linear alignment maps ϕ_nonlin
- Backbone network pre-trained on ImageNet.
- A pair of query and key subcomponents distributed across attention heads performs syntax-boundary routingfinding0.660VPD recovers an attention algorithm for routing across syntactic boundaries, distributed across heads.
- CIMC's current formalization of coherence-maximization as distributed message-passing where processing units negotiate mutual consistency