用分段连续的伏尔泰拉网络提升图像分类，参数更少速度更快。
VNODE: A Piecewise Continuous Volterra Neural Network
- 结合离散伏尔泰拉特征提取与连续微分方程演进
- 在CIFAR10和ImageNet1K上超越现有模型
- 参数量显著降低，计算复杂度更优
本文提出伏尔泰拉神经常微分方程（VNODE），一种分段连续的伏尔泰拉神经网络，将非线性伏尔泰拉滤波与连续时间神经常微分方程相结合，用于图像分类。受视觉皮层启发，其中离散事件处理与连续积分交替进行，VNODE 在离散伏尔泰拉特征提取与基于微分方程的状态演化之间交替。该混合架构在捕捉复杂模式的同时，相比传统深度模型显著减少参数量。在CIFAR10和ImageNet1K等基准数据集上，VNODE持续优于当前最优模型，并展现出更优的计算复杂度。
原文摘要 · Abstract (English)
This paper introduces Volterra Neural Ordinary Differential Equations (VNODE), a piecewise continuous Volterra Neural Network that integrates nonlinear Volterra filtering with continuous time neural ordinary differential equations for image classification. Drawing inspiration from the visual cortex, where discrete event processing is interleaved with continuous integration, VNODE alternates between discrete Volterra feature extraction and ODE driven state evolution. This hybrid formulation captures complex patterns while requiring substantially fewer parameters than conventional deep architectures. VNODE consistently outperforms state of the art models with improved computational complexity as exemplified on benchmark datasets like CIFAR10 and Imagenet1K.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。