concept
active
concept:effective-information-eiEffective Information (EI)
Core measure of causal effect in Hoel's theory; mutual information between uniform input and output distributions.
Neighborhood — ranked by edge-count
Frameworks (3)
framework
- Hoel's Causal Emergence TheoryimplementsQuantitative emergence theory based on Markov dynamics and effective information (EI).
- Neural Information Squeezer Plus (NIS+)implementsExtension of NIS that directly maximizes effective information using probability reweighting.
- Causal GeometryimplementsChvykov and Hoel's geometric extension of causal emergence to continuous systems using Fisher information.
Methods (1)
method
- Ordinal Partition Network (OPN)implementsMethod to discretize continuous time series for EI computation by ranking sub-series.
Concepts (3)
concept
- Causal Emergenceassociated_withCore concept: degree to which an agent exerts unique predictive power on its future; key to cognition at all scales.
- Effect Coefficient (Eff)associated_withNormalized EI bounded 0-1, decomposed into determinism minus degeneracy.
- Do Operatorassociated_withPearl's causal intervention operator used in EI definition to set input distribution uniform.
Hypotheses (1)
hypothesis
- Proposed conjecture in §4.3.1.
Artifacts (1)
artifact
- This review paper surveys quantitative theories of causal emergence and their connections to machine learning.
Findings (1)
finding
- From Klein & Hoel (2020) analysis of artificial complex networks.
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.
- EI divided by output dimension, facilitating comparison across scales.
- Existing approach to standardized electronic communication between organizations; Elephant aimed at improving beyond fixed formats like X12.
- Information shared across all sources in PID.
- Economic concept related to epistemic value in expected free energy; information needed to realize rewards
- EI and normalized EI could serve as a unified metric for out-of-distribution generalization.claim0.715Conjecture that maximizing EI yields causal representations invariant to distribution shifts.
- Game condition where players do not know the exact money values held by opponents, only counts.
- Technique to estimate the continuous EI formula by sampling, used in neural network EI calculation.
- Proposed theoretical framework combining qualitative and quantitative aspects of information, with explicit treatment of processes and information flow; central organizing concept for the paper.