framework
active
framework:neural-information-squeezer-plus-nisNeural Information Squeezer Plus (NIS+)
Extension of NIS that directly maximizes effective information using probability reweighting.
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Mingzhe Yangintroduces
Methods (1)
method
- Kernel Density Estimation (KDE)implementsUsed in NIS+ to estimate natural distribution p(yt) for inverse probability weight.
Concepts (1)
concept
- Effective Information (EI)implementsCore measure of causal effect in Hoel's theory; mutual information between uniform input and output distributions.
Frameworks (1)
framework
- Neural Information Squeezer (NIS)extendsrelated_toMachine learning framework for causal emergence identification via encoder-dynamics learner-decoder architecture.
Artifacts (1)
artifact
- This review paper surveys quantitative theories of causal emergence and their connections to machine learning.
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.
- Yang et al. (2023) result linking EI maximization to robust generalization.
- Real brain imaging result suggesting a compressed emergent representation.
- Central claim of the machine-learning section, summarizing the contribution.
- NIS+ learns macro-dynamics matching ground-truth SIR dynamics from noisy micro-level data.finding0.708Experimental result from Yang et al. (2023) reported in the survey.
- Cognition in nervous systems, used as a modelling target
- Yang et al. (2023) demonstration of emergent pattern recognition.
- Contrast to movie-watching condition, showing context-dependent emergence.
- NIS+ automatically discovers two-group macro-states in Boid model simulations matching the two boid groups.finding0.684Yang et al. (2023) experiment on emergent herding behavior.