AI RESEARCH

Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs

arXiv CS.LG

ArXi:2604.24356v1 Announce Type: cross What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate over the continuum--real-valued states evolved by real-valued dynamics--even when the target functions are discrete. We study them through primitive recursion.