Adaptive KalmanNet: Data-Driven Kalman Filter with Fast Adaptation

1 code implementation • 13 Sep 2023 • Xiaoyong Ni, Guy Revach, Nir Shlezinger

Combining the classical Kalman filter (KF) with a deep neural network (DNN) enables tracking in partially known state space (SS) models.

Language Modelling Large Language Model

Unsupervised Learned Kalman Filtering

1 code implementation • 18 Oct 2021 • Guy Revach, Nir Shlezinger, Timur Locher, Xiaoyong Ni, Ruud J. G. van Sloun, Yonina C. Eldar

In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervised manner, i. e., without requiring ground-truth states.

RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint)

2 code implementations • 10 Oct 2021 • Guy Revach, Xiaoyong Ni, Nir Shlezinger, Ruud J. G. van Sloun, Yonina C. Eldar

The smoothing task is core to many signal processing applications.

KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

2 code implementations • 21 Jul 2021 • Guy Revach, Nir Shlezinger, Xiaoyong Ni, Adria Lopez Escoriza, Ruud J. G. van Sloun, Yonina C. Eldar

State estimation of dynamical systems in real-time is a fundamental task in signal processing.