concept
active
concept:feature-engineeringFeature engineering
Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Covariance-based Sequence Poolingassociated_with
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.
- Interpretable concept representations hypothesized as basic units of computation.
- Internal concepts a model uses, extracted as human-interpretable components.
- Synthesizing inputs maximizing component activation.
- Frequency-weighted spectral value πkλkj determining which features are retained.
- Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
- Extra feature representing unexplained error to make isomorphism exact.
- Decoder direction of a feature changing across layers.
- Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link