For shallow polynomial networks over finite fields, the representable-function count is computed exactly for (n,1,k) and (n,2,k), and collapses to a linear-matrix count when the activation degree is a power of the field characteristic.
Title resolution pending
1 Pith paper cite this work, alongside 93 external citations. Polarity classification is still indexing.
1
Pith paper citing it
93
external citations · OpenAlex
fields
math.AG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Expressivity of Shallow Neural Networks Over Finite Fields
For shallow polynomial networks over finite fields, the representable-function count is computed exactly for (n,1,k) and (n,2,k), and collapses to a linear-matrix count when the activation degree is a power of the field characteristic.