concept
active
concept:second-momentsSecond moments
Statistical moments capturing pairwise feature co-occurrence patterns; the core insight is that second moments preserve structure that first moments destroy.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Covariance-based Sequence Poolingimplements
Concepts (2)
concept
- Geometry of featuresassociated_withResearch thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
- Feature co-occurrenceassociated_withPatterns of which features activate together across tokens; preserved by covariance pooling but lost in mean pooling.
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.
- Statistical moments capturing per-feature central tendency; the paper argues first-moment pooling (mean pooling) destroys joint activation structure.
- Core interpretive claim generalizing beyond genomics; argues mean pooling discards information present in covariance.
- DeepSeek's description of models autonomously learning to self-reflect during training
- CIMC's proposed computational structure of consciousness: perception that perception is occurring, non-inferential and synchronous with its content
- Overarching contemplative principle framing alignment as fluid responsivity to unfolding experience rather than fixed goals
- The design approach of perfecting each room individually before worrying about overall plan coherence.
- Understanding aha moments: from external observations to internal mechanisms (Yang et al., 2025)concept0.660Related work examining the aha moment phenomenon comparing reasoning and non-reasoning models linguistically