CORTEXA
← Browse
arxivmath.AGcs.NE2026-07-19

Expressivity of Shallow Neural Networks Over Finite Fields

Maksym Zubkov, Carol Wu, Shiwei Yang, Param Mody, Yifei Chen

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.

View free PDFSource page

Related papers

arxivq-bio.NCcs.LGcs.NE2026-06-26

CANNs: A Toolkit for Research on Continuous Attractor Neural Networks

Sichao He, Aiersi Tuerhong, Shangjun She, Tianhao Chu, Yuling Wu, Junfeng Zuo, et al.

Continuous attractor neural networks (CANNs) are the canonical computational framework for how the brain encodes continuous variables such as spatial position, head direction, and movement direction, and explain the activity of hippocampal place cells, entorhinal grid cells, and…

View free PDFSource page
arxivcs.ETcs.NEq-bio.NC2026-07-15

Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks

Martin Schottlender, Veronika Volkova, Pengjie Zhou, Ruifeng Zheng, Frank H. P. Fitzek, Pit Hofmann

Interfacing with Biological Neural Networks (BNNs) requires encoding information into stimulation patterns that can be effectively processed and that enable the underlying system to adapt. Nevertheless, the role of stimulation encoding remains poorly understood. In this work, we…

View free PDFSource page
arxivcs.NEcs.AI2026-07-17

Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design

Xu Yang, Mingyang Yu, Jing Xu, Keqian Li

Physics-informed neural networks (PINNs) are unusually sensitive to interacting choices of architecture, activation, loss weighting, collocation, optimization, and constraint enforcement. Large language models (LLMs) can propose these choices, but independent recommendations do n…

View free PDFSource page
arxivcs.NEcs.CVcs.RO2026-07-15

Visual Place Recognition Using Rate-Encoded Spiking Neural Networks with Discrete STDP Learning

Altzi Tsanko, Oikonomou Katerina Maria, Antonios Gasteratos

Spiking Neural Networks (SNNs) trained through unsupervised Spike-Timing-Dependent Plasticity (STDP) have been explored as solutions to visual loop closure problems, driven by the prospect of efficient on-device inference on neuromorphic devices. State-of-the-art STDP-based model…

View free PDFSource page
arxivcs.NEcs.LGnlin.AO2026-07-01

Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplings

Riley Acker, Aman Desai, Garrett Kenyon, Frank Barrows

Oscillatory neural networks (ONNs) have emerged as a promising neuromorphic architecture, leveraging coupled dynamical systems to perform computation and represent information through phase relationships. Their interactions can be designed to support intrinsic energy-minimizing d…

View free PDFSource page