Search Results for author: Shahin Khobahi

Found 11 papers, 3 papers with code

One-Bit Compressive Sensing: Can We Go Deep and Blind?

no code implementations13 Mar 2022 Yiming Zeng, Shahin Khobahi, Mojtaba Soltanalian

The proposed deep architecture is able to learn an alternative sensing matrix by taking advantage of the underlying unfolded algorithm such that the resulting learned recovery algorithm can accurately and quickly (in terms of the number of iterations) recover the underlying compressed signal of interest from its one-bit noisy measurements.

Compressive Sensing

LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers

1 code implementation5 Feb 2021 Shahin Khobahi, Nir Shlezinger, Mojtaba Soltanalian, Yonina C. Eldar

The need to recover high-dimensional signals from their noisy low-resolution quantized measurements is widely encountered in communications and sensing.

Unfolded Algorithms for Deep Phase Retrieval

no code implementations21 Dec 2020 Naveed Naimipour, Shahin Khobahi, Mojtaba Soltanalian

Exploring the idea of phase retrieval has been intriguing researchers for decades, due to its appearance in a wide range of applications.

Retrieval

Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA

no code implementations15 Nov 2020 Zahra Esmaeilbeig, Shahin Khobahi, Mojtaba Soltanalian

In this work, we consider the application of model-based deep learning in nonlinear principal component analysis (PCA).

UPR: A Model-Driven Architecture for Deep Phase Retrieval

no code implementations9 Mar 2020 Naveed Naimipour, Shahin Khobahi, Mojtaba Soltanalian

The problem of phase retrieval has been intriguing researchers for decades due to its appearance in a wide range of applications.

Retrieval

Efficient Waveform Covariance Matrix Design and Antenna Selection for MIMO Radar

1 code implementation13 Feb 2020 Arindam Bose, Shahin Khobahi, Mojtaba Soltanalian

In this paper, we investigate the joint optimization of the waveform covariance matrix and the antenna position vector for a MIMO radar system to approximate a given transmit beam-pattern, as well as to minimize the cross-correlation between the probing signals at a number of given target locations.

Deep-URL: A Model-Aware Approach To Blind Deconvolution Based On Deep Unfolded Richardson-Lucy Network

no code implementations3 Feb 2020 Chirag Agarwal, Shahin Khobahi, Arindam Bose, Mojtaba Soltanalian, Dan Schonfeld

The lack of interpretability in current deep learning models causes serious concerns as they are extensively used for various life-critical applications.

Deep Radar Waveform Design for Efficient Automotive Radar Sensing

no code implementations17 Dec 2019 Shahin Khobahi, Arindam Bose, Mojtaba Soltanalian

In radar systems, unimodular (or constant-modulus) waveform design plays an important role in achieving better clutter/interference rejection, as well as a more accurate estimation of the target parameters.

Autonomous Vehicles Radar waveform design

Deep One-bit Compressive Autoencoding

no code implementations10 Dec 2019 Shahin Khobahi, Arindam Bose, Mojtaba Soltanalian

Parameterized mathematical models play a central role in understanding and design of complex information systems.

Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

1 code implementation27 Nov 2019 Shahin Khobahi, Mojtaba Soltanalian

Parameterized mathematical models play a central role in understanding and design of complex information systems.

Compressive Sensing Quantization

Deep Signal Recovery with One-Bit Quantization

no code implementations30 Nov 2018 Shahin Khobahi, Naveed Naimipour, Mojtaba Soltanalian, Yonina C. Eldar

Machine learning, and more specifically deep learning, have shown remarkable performance in sensing, communications, and inference.

BIG-bench Machine Learning Inference Optimization +1

Cannot find the paper you are looking for? You can Submit a new open access paper.