method
active
method:gaussian-noise-coarsening-analysisGaussian noise coarsening analysis
Adds noise to reveal multi-scale structure.
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Motivates noise analysis.
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.
- Fig. 7d,e.
- Method to aggregate nodes in complex networks to maximize EI, proposed by Klein & Hoel.
- Griebenow et al.'s method: eigenvalue decomposition of TPM, then OPTICS clustering to find macro-nodes.
- Method used to identify the periodic features and their periods in Llama-3.1-8B's MLP neurons
- Mechanism by which superposition works: small neural networks exploit sparsity to approximately simulate much larger sparse networks
- The mechanism by which LLMs generate text: drawing a token from the next-token distribution and appending it to context repeatedly
- State estimation that combines prior expectations with likelihood; updates informed by past and future states.