VNODE: A Piecewise Continuous Volterra Neural Network
This addresses image classification with a novel hybrid approach, though it appears incremental as it combines existing techniques.
The paper tackled image classification by integrating nonlinear Volterra filtering with neural ODEs into a piecewise continuous model, resulting in consistent outperformance of state-of-the-art models with improved computational complexity on benchmarks like CIFAR10 and Imagenet1K.
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.