Guy Revach
YOU?
Author Swipe
View article: Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter
Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter Open
View article: SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation
SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation Open
Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of direction of arrival (DoA) estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and…
View article: AI-Aided Kalman Filters
AI-Aided Kalman Filters Open
The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. These methods are used for state estimation of dynamic systems by relying on mathematical representations in the form of simple state-sp…
View article: Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces Open
People with brain or spinal cord-related paralysis often need to rely on others for basic tasks, limiting their independence. A potential solution is brain-machine interfaces (BMIs), which could allow them to voluntarily control external d…
View article: DEEP AUGMENTED MUSIC ALGORITHM FOR DATA-DRIVEN DOA ESTIMATION
DEEP AUGMENTED MUSIC ALGORITHM FOR DATA-DRIVEN DOA ESTIMATION Open
Direction of arrival (DoA) estimation is a crucial task in sensor array signal processing, giving rise to various successful model-based (MB) algorithms as well as recently developed data-driven (DD) methods. This paper introduces a new hy…
View article: HKF: Hierarchical Kalman Filtering With Online Learned Evolution Priors for Adaptive ECG Denoising
HKF: Hierarchical Kalman Filtering With Online Learned Evolution Priors for Adaptive ECG Denoising Open
Electrocardiography (ECG) signals play a pivotal role in many healthcare applications, especially in at-home monitoring of vital signs. Wearable technologies, which these applications often depend upon, frequently produce low-quality ECG s…
View article: Latent-KalmanNet: Learned Kalman Filtering for Tracking From High-Dimensional Signals
Latent-KalmanNet: Learned Kalman Filtering for Tracking From High-Dimensional Signals Open
The Kalman filter (KF) is a widely used algorithm for tracking dynamic systems that are captured by state space (SS) models. The need to fully describe an SS model limits its applicability under complex settings, e.g., when tracking based …
View article: DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm
DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm Open
Direction of arrival (DoA) estimation of multiple signals is pivotal in sensor array signal processing. A popular multisignal DoA estimation method is the multiple signal classification (MUSIC) algorithm, which enables high-performance sup…
View article: Outlier-Insensitive Kalman Filtering: Theory and Applications
Outlier-Insensitive Kalman Filtering: Theory and Applications Open
State estimation of dynamical systems from noisy observations is a fundamental task in many applications. It is commonly addressed using the linear Kalman filter (KF), whose performance can significantly degrade in the presence of outliers…
View article: Adaptive KalmanNet: Data-Driven Kalman Filter with Fast Adaptation
Adaptive KalmanNet: Data-Driven Kalman Filter with Fast Adaptation Open
Combining the classical Kalman filter (KF) with a deep neural network (DNN) enables tracking in partially known state space (SS) models. A major limitation of current DNN-aided designs stems from the need to train them to filter data origi…
View article: Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter
Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter Open
Recent years have witnessed a growing interest in tracking algorithms that augment Kalman Filters (KFs) with Deep Neural Networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a …
View article: NUV-DoA: NUV Prior-based Bayesian Sparse Reconstruction with Spatial Filtering for Super-Resolution DoA Estimation
NUV-DoA: NUV Prior-based Bayesian Sparse Reconstruction with Spatial Filtering for Super-Resolution DoA Estimation Open
Achieving high-resolution Direction of Arrival (DoA) recovery typically requires high Signal to Noise Ratio (SNR) and a sufficiently large number of snapshots. This paper presents NUV-DoA algorithm, that augments Bayesian sparse reconstruc…
View article: SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation
SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation Open
Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of DoA estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and noise subspaces. Subsp…
View article: Latent-KalmanNet: Learned Kalman Filtering for Tracking from High-Dimensional Signals
Latent-KalmanNet: Learned Kalman Filtering for Tracking from High-Dimensional Signals Open
The Kalman filter (KF) is a widely-used algorithm for tracking dynamic systems that are captured by state space (SS) models. The need to fully describe a SS model limits its applicability under complex settings, e.g., when tracking based o…
View article: HKF: Hierarchical Kalman Filtering with Online Learned Evolution Priors for Adaptive ECG Denoising
HKF: Hierarchical Kalman Filtering with Online Learned Evolution Priors for Adaptive ECG Denoising Open
Electrocardiography (ECG) signals play a pivotal role in many healthcare applications, especially in at-home monitoring of vital signs. Wearable technologies, which these applications often depend upon, frequently produce low-quality ECG s…
View article: LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control
LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control Open
Stochastic control deals with finding an optimal control signal for a dynamical system in a setting with uncertainty, playing a key role in numerous applications. The linear quadratic Gaussian (LQG) is a widely-used setting, where the syst…
View article: Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Trading
Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Trading Open
Pairs trading is a family of trading techniques that determine their policies based on monitoring the relationships between pairs of assets. A common pairs trading approach relies on describing the pair-wise relationship as a linear Space …
View article: Outlier-Insensitive Kalman Filtering Using NUV Priors
Outlier-Insensitive Kalman Filtering Using NUV Priors Open
The Kalman filter (KF) is a widely-used algorithm for tracking the latent state of a dynamical system from noisy observations. For systems that are well-described by linear Gaussian state space models, the KF minimizes the mean-squared err…
View article: Anomaly Search over Composite Hypotheses in Hierarchical Statistical Models
Anomaly Search over Composite Hypotheses in Hierarchical Statistical Models Open
Detection of anomalies among a large number of processes is a fundamental task that has been studied in multiple research areas, with diverse applications spanning from spectrum access to cyber-security. Anomalous events are characterized …
View article: KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics Open
State estimation of dynamical systems in real-time is a fundamental task in\nsignal processing. For systems that are well-represented by a fully known\nlinear Gaussian state space (SS) model, the celebrated Kalman filter (KF) is a\nlow com…
View article: Unsupervised Learned Kalman Filtering
Unsupervised Learned Kalman Filtering Open
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., wi…
View article: RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint)
RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint) Open
The smoothing task is core to many signal processing applications. A widely popular smoother is the Rauch-Tung-Striebel (RTS) algorithm, which achieves minimal mean-squared error recovery with low complexity for linear Gaussian state space…
View article: Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models
Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models Open
Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the un…
View article: DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm
DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm Open
Direction of arrival (DoA) estimation of multiple signals is pivotal in sensor array signal processing. A popular multi-signal DoA estimation method is the multiple signal classification (MUSIC) algorithm, which enables high-performance su…
View article: KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics Open
State estimation of dynamical systems in real-time is a fundamental task in signal processing. For systems that are well-represented by a fully known linear Gaussian state space (SS) model, the celebrated Kalman filter (KF) is a low comple…