Results 21 to 30 of about 5,685 (163)

Gradient Estimation for Ultra Low Precision POT and Additive POT Quantization

open access: yesIEEE Access, 2023
Deep learning networks achieve high accuracy for many classification tasks in computer vision and natural language processing. As these models are usually over-parameterized, the computations and memory required are unsuitable for power-constrained ...
Huruy Tesfai   +4 more
doaj   +1 more source

One-bit quantization is good for programmable coding metasurfaces

open access: yesScience China Information Sciences, 2022
The information-carrying programmable metasurfaces has found widespread applications in communication, sensing, and other related areas. However, there is a fundamental but unresolved problem, i.e., the rigorous understanding of the quantization of metasurface coding.
Shuang, Ya   +7 more
openaire   +2 more sources

One-bit quantizers for fading channels

open access: yesCoRR, 2011
4 pages. To be presented at the 2012 International Zurich Seminar on Communications (IZS)
Koch, Tobias, Lapidoth, Amos
openaire   +3 more sources

ALigN: A Highly Accurate Adaptive Layerwise Log_2_Lead Quantization of Pre-Trained Neural Networks

open access: yesIEEE Access, 2020
Deep Neural Networks are one of the machine learning techniques which are increasingly used in a variety of applications. However, the significantly high memory and computation demands of deep neural networks often limit their deployment on embedded ...
Siddharth Gupta   +4 more
doaj   +1 more source

SANA: Sensitivity-Aware Neural Architecture Adaptation for Uniform Quantization

open access: yesApplied Sciences, 2023
Uniform quantization is widely taken as an efficient compression method in practical applications. Despite its merit of having a low computational overhead, uniform quantization fails to preserve sensitive components in neural networks when applied with ...
Mingfei Guo, Zhen Dong, Kurt Keutzer
doaj   +1 more source

1-Bit Reconfigurable Beam Steering Planar Array Antenna Based on Reflectarray Feeding

open access: yesIEEE Access, 2023
In this paper, we present a method for reducing the quantization lobe in a 1-bit beam steering planar array antenna. The method is inspired by reflectarray feeding in such a way that as we move away from the center of the array, the phase becomes more ...
Pooria Kabiri   +2 more
doaj   +1 more source

One-bit Multi-modality Jamming Method against SAR

open access: yesLeida xuebao, 2022
This paper proposes a one-bit multi-modality jamming method against Synthetic Aperture Radar (SAR). After being intercepted by the jammer, the SAR signal is quantized to one-bit sampling data through comparison with the single-frequency threshold ...
Bo ZHAO, Ji CHEN, Lei HUANG
doaj   +1 more source

Approximation of capacity for ISI channels with one-bit output quantization [PDF]

open access: yes2015 IEEE International Symposium on Information Theory (ISIT), 2015
Motivated by recent high bandwidth communication systems, Inter-Symbol Interference (ISI) channels with 1-bit quantized output are considered under an average-power-constrained continuous input. While the exact capacity is difficult to characterize, an approximation that matches with the exact channel output up to a probability of error is provided ...
Radha Krishna Ganti   +2 more
openaire   +2 more sources

Limited feedback in multiple-antenna systems with one-bit quantization [PDF]

open access: yes2015 49th Asilomar Conference on Signals, Systems and Computers, 2015
Communication systems with low-resolution analog-to-digital-converters (ADCs) can exploit channel state information at the transmitter (CSIT) and receiver. This paper presents initial results on codebook design and performance analysis for limited feedback systems with one-bit ADCs.
Jianhua Mo 0001, Robert W. Heath Jr.
openaire   +2 more sources

Evaluation of Model Quantization Method on Vitis-AI for Mitigating Adversarial Examples

open access: yesIEEE Access, 2023
Adversarial examples (AEs) are typical model evasion attacks and security threats in deep neural networks (DNNs). One of the countermeasures is adversarial training (AT), and it trains DNNs by using a training dataset containing AEs to achieve robustness
Yuta Fukuda   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy