Neural Information Squeezer (NIS)

Machine learning framework for causal emergence identification via encoder-dynamics learner-decoder architecture.

Neighborhood — ranked by edge-count

thinker

concept

Information Bottleneck
implements
Compression-prediction trade-off; NIS encodes micro-states through an information bottleneck.

framework

Neural Information Squeezer Plus (NIS+)
extendsrelated_to
Extension of NIS that directly maximizes effective information using probability reweighting.
Hoel's Causal Emergence Theory
implements
Quantitative emergence theory based on Markov dynamics and effective information (EI).

artifact

Yuan 2023 Emergence and Causality in Complex Systems: A Survey
mentions
This review paper surveys quantitative theories of causal emergence and their connections to machine learning.

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.

The NIS and NIS+ frameworks provide effective solutions for causal emergence identification from data.claim0.722
Central claim of the machine-learning section, summarizing the contribution.
neural cognitionconcept0.720
Cognition in nervous systems, used as a modelling target
Neural codeconcept0.719
The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
NIS+ outperforms NIS, variational autoencoders, and feed-forward neural networks in out-of-distribution generalization experiments.finding0.709
Yang et al. (2023) result linking EI maximization to robust generalization.
Neural Annealingframework0.707
Michael Johnson's prior work on how neural networks (and brains) can be 'annealed' to find optimal states.
NIS+ learns macro-dynamics matching ground-truth SIR dynamics from noisy micro-level data.finding0.706
Experimental result from Yang et al. (2023) reported in the survey.
Neuroscienceinstitute0.705
In AOMIC ID1000 movie-watching fMRI data, NIS+ finds a one-dimensional macro-state representing 100-dimensional micro-states.finding0.702
Real brain imaging result suggesting a compressed emergent representation.