Hierarchical Models of Sensory Generation

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• hierarchical modelsmethod0.828
  Models of sensory generation that allow dynamic context-sensitive prior expectations.
• Hierarchical Reasoning Model (HRM)method0.762
  Cited small (7M param) recurrent model that outperforms >10B-parameter LLMs on ARC-AGI, motivating the paper's focus on reasoning dynamics.
• How do biological organisms evolve their generative model to account for new sensory observations?question0.757
  Structure learning challenge in Discussion.
• Hierarchically Mechanistic Mindframework0.751
• Performance-optimized hierarchical models predict neural responses in higher visual cortex (Yamins et al., 2014)concept0.750
  Demonstrated CNN representations predict neurons in visual cortex; background motivation for neural-network-brain correspondence.
• Hyper Generative-Modelconcept0.745
  Globally-acting model that recursively monitors and updates how all inference layers interact; substrate of epistemic depth
• Connectionist models of cognition and learning identify conditions where collective intelligence can arise bottom-up, using only distributed learning mechanisms without system-level or global feedback.claim0.735
  Central claim about the power of connectionism.
• causal structure of sensory contingenciesconcept0.734
  Statistical regularities in sensorium learned by perceptual and value mechanisms.