SOURCE-LINKED INTELLIGENCE

Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Time-series data across physical and biological domains are fundamentally driven by complex, non-stationary oscillatory modes. While deep learning models, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks, and Transformers, have dominated sequential analysis, they remain fundamentally "spectral-blind". By mapping continuous physical waves into unconstrained spatial or discrete token spaces, these architectures suffer from severe spectral entanglement, acting as opaque black boxes that decouple predictive accuracy from physical reality. In this paper, we introduce the Freq

Read original source ↗ Open in workspace

recordType

paper

region

Global