Machine Learning-Based State Space Modeling

AI-discovered pathway models that reconstruct decision landscapes and enable prediction of novel interventions in collective decision-making systems.

Neighborhood — ranked by edge-count

finding

Melanoma conversion is all-or-none at animal level despite population variation
supports
In tadpoles with disrupted bioelectric signaling: different reagents produce 0-100% conversion rates in populations, but individual animals are entirely converted or entirely normal—collective decision-making phenomenon.

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.

Discrete State-Space Modelsconcept0.792
Mathematical formalism used in active inference for modeling hierarchical and discrete brain processes.
Bayesian Model-Based Reinforcement Learningframework0.768
RL variant that maintains beliefs over environment model; compared to active inference using Thompson sampling.
Data-centric machine learningconcept0.766
Approach emphasizing data quality and source identification rather than only model architecture changes.
Unsupervised learning builds a low-dimensional model of the input data.claim0.748
Clarifies what unsupervised learning does.
Attractor in State-Spaceconcept0.748
Small regions in dynamical system state-space to which complex systems converge; cited from complexity theory as partial but insufficient explanation for living structure
Connectionist Machine Learningframework0.744
Analogous framework for understanding how higher-level information arises from lower-level components in a collective system.
This paper provides a complete mathematical synthesis of active inference on discrete state-space models.claim0.743
Self-description of the paper in the abstract.
Multiscale Agent-Based Modelmethod0.743