Shallow interaction structures cannot compute non-linearly separable functions; depth (hidden layers) is necessary for ETI-relevant individuality

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

• Representing non-linearly separable functions requires a network with multiple layers.claim0.818
  Architectural requirement from machine learning.
• Can Shallow Or Reciprocal Interaction Structures Compute Nonlinearlyquestion0.807
• When interactions constitute non-linearly separable functions, it creates a ‘we’; what we are doing becomes a relevant variable.claim0.795
  Explains how non-separability shifts identity from parts to collective.
• Functional relationships required for new individuality level encode non-linearly separable functions and are enacted via information integration and collective actionhypothesis0.791
• The conditions necessary to evolve a new level of individuality are described by the conditions necessary to learn non-decomposable functions (deep model induction)claim0.782
  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)hypothesis0.772
• Hierarchical structure in interaction topology enables complex multiscale patterns that cannot exist in flat networks.claim0.771
  Explains why biological systems achieve organization across scales while language models struggle; grounds in free energy scaling
• ETIs are the evolutionary equivalent of deep learning: (i) required functional relationships encode non-decomposable functions, (ii) these are enacted by basal cognition mechanisms, and (iii) conditions for deep model induction predict ETI occurrence.hypothesis0.767
  Overarching three-part hypothesis stated in introduction