method
active
method:kernel-weighted-dirichlet-poolingKernel-weighted Dirichlet pooling
Gaussian-kernel pooling of counts within segments parameterizing a Dirichlet.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Change point segmentation, kernel Dirichlet pooling, CV tuning.
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.
- Conjugate prior for categorical variables; used for beliefs about likelihood matrix A.
- Learning rule for updating Dirichlet beliefs about likelihood matrix A by adding outer products of observations and state estimates.
- Novel aggregation technique replacing mean pooling; preserves joint activation structure (feature co-occurrence) in token embeddings.
- Measures spatial coherence of concept maps.
- Replacing kernel pooling with flat per-segment pooling raises pooled TVD by 0.0021 for Llama at S=30.finding0.665Ablation.
- On recorded DeepSeek example, Kernel Pooling alone has TVD 0.2720 versus 0.0088 for Full Model.finding0.663Blurred forks.
- Ablation interpretation.
- Connection between learning rule and synaptic plasticity.