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.

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

• 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 cortexfinding0.876
  Empirical evidence for the universality hypothesis cited as supporting the possibility of convergent consciousness-like solutions
• Performance-optimized hierarchical models predict neural responses in higher visual cortex (Yamins et al., 2014)concept0.831
  Demonstrated CNN representations predict neurons in visual cortex; background motivation for neural-network-brain correspondence.
• A vision model trained on ImageNet can be aligned with a model trained on Places-365 while maintaining good performance, and early layers are more interchangeable than later layersfinding0.808
  Lenc & Vedaldi result illustrating data independence in representations and layer-wise alignment
• Alignment with vision models corresponds to improved performance on downstream language tasks including commonsense reasoning and mathclaim0.797
  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.quote0.797
  The paper's central thesis statement, presented prominently after the abstract
• Human consciousness is tied to a biological learning algorithm — the simplest algorithm discoverable by evolutionary search to train a self-organizing biological substrate to become intelligent.claim0.788
  Core theoretical claim connecting consciousness to biological learning
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.787
  The central hypothesis of the paper; the platonic representation hypothesis itself
• We hypothesize that consciousness may be at the heart of a universal biological learning algorithm — one that runs on self-organizing groups of communicating cells sharing evolutionary incentives — and that it creates rather than results from organized mental architecture.hypothesis0.785
  The Genesis Hypothesis as explicit predictive conjecture