Premakumar et al. 2024 - Unexpected benefits of self-modeling in neural systems

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

• Robots capable of self-modeling can model their own body and unexpected damage using AI methods, with morphological and mental changes occurring in parallel.finding0.806
  Evidence for blurring of embodied robot / non-embodied AI distinction through self-modeling
• An artificial model replicating mechanisms of self-illusion can test hypotheses and reveal novel affordances for non-human intelligence.hypothesis0.773
  Methodological proposal to integrate knowledge from contemplative and cognitive science into AI/artificial life frameworks.
• An integrated artificial model can address self-illusion effects on affordances by combining information theory, cognitive science, and philosophy.hypothesis0.766
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.761
  The central hypothesis of the paper; the platonic representation hypothesis itself
• Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.759
  The paper's central thesis statement, presented prominently after the abstract
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.755
  Foundational claim of the paper, defining self-evidencing.
• The earlier a base model (less exposure to LM-related data), the more it is surprised by its own spontaneous self-referential capabilities.claim0.755
  Claim that capability emerges from architecture, not data, and that later models lose the surprise.
• Hebbian learning in a self-modelling dynamical system effects a positive feedback on correlations; the more things co-occur, the more the connection between them changes to make them more likely to co-occur in future.claim0.754
  Describes the self-reinforcing nature of Hebbian learning in networks.