Paper ID | MLSP-41.4 | ||
Paper Title | KALMANNET: DATA-DRIVEN KALMAN FILTERING | ||
Authors | Guy Revach, ETH Zurich, Switzerland; Nir Shlezinger, Ben-Gurion University of the Negev, Israel; Ruud J. G. van Sloun, Eindhoven University of Technology, and with Phillips Research, Netherlands; Yonina C. Eldar, Weizmann Institute of Science, Israel | ||
Session | MLSP-41: Deep Learning Optimization | ||
Location | Gather.Town | ||
Session Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | The Kalman filter (KF) is a celebrated signal processing algorithm, implementing optimal state estimation of dynamical systems that are well represented by a linear Gaussian state space model. The KF is model-based, and therefore relies on full and accurate knowledge of the underlying model. We present KalmanNet, a hybrid data-driven/model-based filter that does not require full knowledge of the underlying model parameters. KalmanNet is inspired by the classical KF flow and implemented by integrating a dedicated and compact neural network for the Kalman gain computation. We present an offline training method, and numerically illustrate that KalmanNet can achieve optimal performance without full knowledge of the model parameters. We demonstrate that when facing inaccurate parameters KalmanNet learns to achieve notably improved performance compared to KF. |