A class of time-varying deep state-space model neural networks is proposed that learns dynamics via a dictionary of basis functions evolving differently over time, outperforming time-invariant versions on switching synthetic data and speech denoising.
The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
Time-Varying Deep State Space Models for Sequences with Switching Dynamics
A class of time-varying deep state-space model neural networks is proposed that learns dynamics via a dictionary of basis functions evolving differently over time, outperforming time-invariant versions on switching synthetic data and speech denoising.
- BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series