arXiv · 2607.17090
Expressivity of Shallow Neural Networks Over Finite Fields
Abstract
We study the expressivity of shallow polynomial neural networks (PNNs) with monomial activation functions over finite fields. For a given architecture, we define a neuromanifold as the image of the map from all possible network weights into the product of polynomial rings. We quantify the expressivity by the cardinality of the neuromanifold, and derive a natural lower and upper bound. This leads to counting rational points over finite fields, a problem closely linked to the Weil conjectures. Finally, we present an architecture that exhibits a striking difference in the neuromanifolds when considered over a characteristic zero versus a finite-characteristic field, illustrating the critical role of field characteristic in the notion of expressivity.
Explore related subjects
Keep this discovery
Maksym Zubkov, Carol Wu, Shiwei Yang, Param Mody, Yifei Chen. 2026-07-19. Expressivity of Shallow Neural Networks Over Finite Fields. https://arxiv.org/abs/2607.17090
Cite the original work for its findings. Save a collection to share your selection of sources.