
HY
Haoyu Yun, Hamid Krim, Yufang Bao
· 1 min read
ResearcharXiv cs.CV
Learning with Volterra Neural Networks: A System Theoretic Perspective
arXiv:2609.01928v2 Announce Type: replace
Abstract: Higher-order interaction components are important for signal, image, and video modeling, but explicit high-order operators often suffer from rapidly increasing parameter and computational costs. This paper presents kVNN, a learnable kernelized Volterra Neural operator for compact higher-order filtering. The motivation is to use kernelization to improve the efficiency of Volterra-type neural operators while providing a structured interpretation of their higher-order components. The proposed formulation combines the order-wise structure of Volterra filtering with learnable polynomial-kernel atoms, allowing different interaction orders to be represented by separate learnable centers and coefficients. This order-decoupled representation avoids explicit high-order tensor parameterization and can be implemented as a CNN-compatible layer. Experiments on representative vision tasks show that kVNN achieves a favorable accuracy--efficiency trade-off.
Original source
This story was published by arXiv cs.CV and written by Haoyu Yun, Hamid Krim, Yufang Bao. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


