Academic paper on autoencoders for signal processing. Addresses parameter estimation in multi-component damped sinusoidal signals using neural networks.
Research
Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals
Autoencoders can directly learn to extract parameters from overlapping damped sinusoidal signals, bypassing traditional Fourier-based signal decomposition methods.
Tuesday, April 7, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
research