Results 11 to 20 of about 5,685 (163)
Adversarial Robustness by One Bit Double Quantization for Visual Classification [PDF]
IEEE Access, 2019 In this paper, we propose a novel robust visual classification framework that uses double quantization (dquant) to defend against adversarial examples in a specific attack scenario called “subsequent adversarial examples” where test images ...
Maungmaung Aprilpyone +2 more
doaj +2 more sources
2022 IEEE International Symposium on Information Theory (ISIT), 2022 We consider the one-bit quantizer that minimizes the mean squared error for a source living in a real Hilbert space. The optimal quantizer is a projection followed by a thresholding operation, and we provide methods for identifying the optimal direction along which to project.
Sourbh Bhadane, Aaron B. Wagner
openaire +2 more sources
Deep Signal Recovery with One-bit Quantization [PDF]
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019 Machine learning, and more specifically deep learning, have shown remarkable performance in sensing, communications, and inference. In this paper, we consider the application of the deep unfolding technique in the problem of signal reconstruction from its one-bit noisy measurements.
Shahin Khobahi +3 more
openaire +2 more sources
Turbo decoding with one bit extrinsic quantization [PDF]
IEEE Communications Letters, 2005 The quantization of extrinsic information passed between two component decoders in a classical binary turbo decoder is considered and it is found that decoding with only a single bit of precision is possible. The proposed quantization scheme is studied via EXIT analysis using a BSC (Binary Symmetric Channel) model.
Lukasz Krzymien, Christian Schlegel
openaire +1 more source
Covariance estimation under one-bit quantization
The Annals of Statistics, 2022 We consider the classical problem of estimating the covariance matrix of a subgaussian distribution from i.i.d. samples in the novel context of coarse quantization, i.e., instead of having full knowledge of the samples, they are quantized to one or two bits per entry. This problem occurs naturally in signal processing applications.
Dirksen, Sjoerd +2 more
openaire +5 more sources
Learning to Decode Polar Codes With One-Bit Quantizer [PDF]
IEEE Access, 2020 A deep learning method for improving the performance of polar belief propagation (BP) decoder equipped with a one-bit quantizer is proposed. The method generalizes the standard polar BP algorithm by assigning weights to the layers of the unfolded factor graph. These weights can be learned autonomously using deep learning techniques.
Jian Gao 0013 +2 more
openaire +2 more sources
Covariance Estimation under One‐bit Quantization [PDF]
PAMM, 2021 AbstractWe consider the classical problem of estimating the covariance matrix of a subgaussian distribution from i.i.d. samples in the novel context of coarse quantization, i.e., instead of having full knowledge of the samples, they are quantized to one or two bits per entry. This problem occurs naturally in signal processing applications. We introduce
Sjoerd Dirksen +2 more
openaire +1 more source
One-bit splitting deceptive jamming against SAR
Defence Technology, 2022 One-bit quantization is a promising technique due to its performance retention and complexity reduction in a deceptive jammer against synthetic aperture radar (SAR).
Bo Zhao +4 more
doaj +1 more source
DoubleQExt: Hardware and Memory Efficient CNN Through Two Levels of Quantization
IEEE Access, 2021 To fulfil the tight area and memory constraints in IoT applications, the design of efficient Convolutional Neural Network (CNN) hardware becomes crucial. Quantization of CNN is one of the promising approach that allows the compression of large CNN into a
Jin-Chuan See +5 more
doaj +1 more source
Gaussian Multiple Access Channels with One-Bit Quantizer at the Receiver †,‡ [PDF]
Entropy, 2018 The capacity region of a two-transmitter Gaussian multiple access channel (MAC) under average input power constraints is studied, when the receiver employs a zero-threshold one-bit analogue-to-digital converter (ADC). It is proven that the input distributions of the two transmitters that achieve the boundary points of the capacity region are discrete ...
Borzoo Rassouli +2 more
openaire +6 more sources