framework
active
framework:robust-features-hypothesisRobust features hypothesis
Models exploit non-robust but predictive patterns.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Ability to maintain function despite perturbations.
- Area of AI research that uses interventions to test and improve model resilience to perturbations
- The functional solidity and working character of natural systems, arising from the fifteen properties.
- Finds data clusters where response concept is chosen/rejected leaning.
- The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
- Ability to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference
- Synthesizing inputs maximizing component activation.
- Interpretable concept representations hypothesized as basic units of computation.