Performance-optimized hierarchical models predict neural responses in higher visual cortex (Yamins et al., 2014)

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

• Olah et al. (2020) found that automatically trained computer vision models, regardless of architecture and training procedure, all arrive at similar functional structures organizing similar features into similar compositional hierarchies, closely resembling the primate visual cortex.finding0.831
  Empirical finding supporting the Universality Hypothesis; extended by the paper to consciousness
• Diverse computer vision models trained on visual recognition tasks converge to remarkably similar internal feature representations regardless of architecture, training procedure, or implementation details, closely matching the organization of animal visual cortexfinding0.802
  Empirical evidence for the universality hypothesis cited as supporting the possibility of convergent consciousness-like solutions
• Among 78 vision models, those solving more VTAB tasks (higher transfer performance) show higher mutual nearest-neighbor alignment with each otherfinding0.781
  Key empirical finding establishing that representational alignment correlates with model competence
• Any system monitoring and controlling its own processing requires all three hierarchical levels: perception, attention, meta-awareness.claim0.774
  Design principle with implications for AI and consciousness-UX; architectural requirement for self-directed cognition.
• 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.claim0.770
  Central claim about the power of connectionism.
• Among 78 vision models on Places-365, models that solve more VTAB tasks tend to be more aligned with each other, with high-performance models forming a tightly clustered setfinding0.768
  Empirical result showing alignment increases with model competence
• Alignment with vision models corresponds to improved performance on downstream language tasks including commonsense reasoning and mathclaim0.765
  Claims that alignment score is a proxy for general capability
• Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.765
  The paper's central thesis statement, presented prominently after the abstract