Deep Model Induction Equivalence Hypothesis H2

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

• H2: The conditions necessary for the induction of deep models, familiar in connectionist models of learning and cognition, are predictive of the conditions necessary for an ETI to occur.hypothesis0.805
  Second hypothesis linking learning theory directly to evolutionary transitions
• Deep Model Inductionframework0.803
• How Are The Conditions For Deep Model Inductionquestion0.776
• Evolutionary transitions in individuality constitute a form of deep model induction.claim0.743
  Links ETIs to the learning of hierarchical representations.
• Induction heads explain in-context learning in small models and only develop in models with at least two attention layersclaim0.720
  Central empirical claim of the paper; induction heads are shown to be the mechanism for powerful in-context learning
• The conditions necessary to evolve a new level of individuality are described by the conditions necessary to learn non-decomposable functions (deep model induction)claim0.716
  Core interpretive claim of the paper connecting ETIs to connectionist learning
• Conditions necessary to evolve new individuality level are described by conditions for learning non-decomposable functions (deep model induction)hypothesis0.708
• Large models form many induction heads built from K-composition with a previous token head, making induction heads a central driver of in-context learning at all scalesclaim0.706
  Forward-looking claim connecting toy model findings to large-scale language models