concept
active
concept:feature-engineering

Feature 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

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Featuresconcept0.832
    Interpretable concept representations hypothesized as basic units of computation.
  • Internal concepts a model uses, extracted as human-interpretable components.
  • Synthesizing inputs maximizing component activation.
  • Feature utilityconcept0.805
    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.
  • Error featuresconcept0.786
    Extra feature representing unexplained error to make isomorphism exact.
  • Feature driftconcept0.781
    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