Suchergebnisse - low-precision quantization algorithm

An Energy-Efficient Signal Detection Scheme for a Radar-Communication System Based on the Generalized Approximate Message-Passing Algorithm and Low-Precision Quantization

Autoren: De-Ping Xia Yu Zhang Peixiang Cai et al.

Quelle: IEEE Access, Vol 7, Pp 29065-29075 (2019)

Schlagwörter: 0203 mechanical engineering, Integrated radar-communication system, low-precision quantization algorithm, 0202 electrical engineering, electronic engineering, information engineering, GAMP algorithm, energy efficient, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, 7. Clean energy, TK1-9971

Zugangs-URL: https://ieeexplore.ieee.org/ielx7/6287639/8600701/08643366.pdf
https://doaj.org/article/6c7bcdeb66ea4c23a3a0d041c4595e72
https://dblp.uni-trier.de/db/journals/access/access7.html#XiaZCH19

Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models

Autoren: Wang, Xijun Huang, Junyun Abdalla, Rayyan et al.

Schlagwörter: FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Vision and Pattern Recognition

Zugangs-URL: http://arxiv.org/abs/2509.18763

Design of Sparse CNN Accelerator Based on Inter-Frame Data Reuse

Autoren: Qirun HONG, Qin WANG

Quelle: Jisuanji gongcheng, Vol 49, Iss 12, Pp 55-62 (2023)

Schlagwörter: convolutional neural network(cnn), low-precision quantization, inter-frame data reuse, winograd algorithm, accelerator, field programmable gate array(fpga), Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Dateibeschreibung: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/20231206.pdf; https://doaj.org/toc/1000-3428

Zugangs-URL: https://doaj.org/article/87d2ca9278d644bd8d972690081f8952

Neural network quantization: separate scaling of rows and columns in weight matrix.

Autoren: Wang, Xingyu Hu, Yunhe Yang, Zhouwang

Quelle: Neural Computing & Applications. Jan2025, Vol. 37 Issue 3, p1417-1428. 12p.

Schlagwörter: *NONLINEAR programming, *MATRICES (Mathematics), *ALGORITHMS, *FORECASTING, *ATTENTION

A Precision-Scalable Accelerator with Sign-Magnitude Representation and Dual Adder Trees.

Autoren: Hu, Xianghong Yang, Chaoming Li, Xueming et al.

Quelle: ACM Transactions on Embedded Computing Systems; Nov2025, Vol. 24 Issue 6, p1-26, 26p

Schlagwörter: COPROCESSORS, SIGNAL quantization, MECHANICAL efficiency

Reinforcement Learning Based Quantization Strategy Optimal Assignment Algorithm for Mixed Precision.

Autoren: Yuejiao Wang Zhong Ma Chaojie Yang et al.

Quelle: Computers, Materials & Continua; 2024, Vol. 79 Issue 1, p819-836, 18p

Schlagwörter: REINFORCEMENT learning, ARTIFICIAL neural networks, DEEP reinforcement learning, ALGORITHMS, REINFORCEMENT (Psychology)

Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization

Autoren: Xinyu Zhang Ian Colbert Srinjoy Das

Quelle: Applied Sciences, Vol 12, Iss 15, p 7829 (2022)

Schlagwörter: channel pruning, layerwise pruning, quantization, joint pruning, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999

Dateibeschreibung: electronic resource

Relation: https://www.mdpi.com/2076-3417/12/15/7829; https://doaj.org/toc/2076-3417

Zugangs-URL: https://doaj.org/article/7749a2fc55bd4415a03d5ee7d2d8e281

LSFQ: A Low Precision Full Integer Quantization for High-Performance FPGA-Based CNN Acceleration

Autoren: Wenbo Zhang Zhenshan Bao Junnan Guo et al.

Quelle: 2021 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS).

Schlagwörter: 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Zugangs-URL: https://dblp.uni-trier.de/db/conf/coolchips/coolchips2021.html#BaoZ0G21
https://ieeexplore.ieee.org/document/9410327/

模型剪枝与低精度量化融合的DNN 模型压缩算法. (Chinese)

Alternate Title: DNN Model Compression Algorithms Based on Fusion of Model Pruning and Low-precision Quantization. (English)

Autoren: 吴进 杨雪 胡怡青

Quelle: Telecommunication Engineering; 6/28/2020, Vol. 60 Issue 6, p617-624, 8p

Schlagwörter: ARTIFICIAL neural networks, SMARTPHONES, FELIDAE, VETERINARY hospitals, DEEP learning, MOBILE hospitals, PRUNING, DOGS

Adaptive Global Power-of-Two Ternary Quantization Algorithm Based on Unfixed Boundary Thresholds.

Autoren: Sui, Xuefu Lv, Qunbo Ke, Changjun et al.

Quelle: Sensors (14248220); Jan2024, Vol. 24 Issue 1, p1-26, 26p, 8 Charts, 6 Graphs

SpQuant-SNN: ultra-low precision membrane potential with sparse activations unlock the potential of on-device spiking neural networks applications

Autoren: Ahmed Hasssan Jian Meng Anupreetham Anupreetham et al.

Quelle: Frontiers in Neuroscience, Vol 18 (2024)

Schlagwörter: spiking neural networks, quantization, pruning, event data, static images, low-precision, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571

Dateibeschreibung: electronic resource

Relation: https://www.frontiersin.org/articles/10.3389/fnins.2024.1440000/full; https://doaj.org/toc/1662-453X

Zugangs-URL: https://doaj.org/article/290c1efba7224ab0bb0d6bd708e3e84f

Quantization-Based Optimization Algorithm for Hardware Implementation of Convolution Neural Networks.

Autoren: Mohd, Bassam J. Ahmad Yousef, Khalil M. AlMajali, Anas et al.

Quelle: Electronics (2079-9292); May2024, Vol. 13 Issue 9, p1727, 25p

Schlagwörter: CONVOLUTIONAL neural networks, OPTIMIZATION algorithms, ARTIFICIAL neural networks

SEMQ: Efficient non-uniform quantization with sensitivity-based error minimization for large language models.

Autoren: Li, Dongmin Xie, Xiurui Zhang, Dongyang et al.

Quelle: Future Generation Computer Systems. Feb2026, Vol. 175, pN.PAG-N.PAG. 1p.

Schlagwörter: LANGUAGE models, SIGNAL quantization, OUTLIER detection, DATA compression

Energy efficiency joint optimization algorithm for low-precision ADC massive MIMO systems

Autoren: Haiyan CAO Wenjuan HU Yingjuan ZHI et al.

Quelle: Dianxin kexue, Vol 36, Pp 90-96 (2020)

Schlagwörter: massive MIMO, ADC, alternate optimization, energy efficiency, Telecommunication, TK5101-6720, Technology

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/1000-0801

Zugangs-URL: https://doaj.org/article/554a81a471024b5996ec1ed4a1d19ca7

FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs

Autoren: Xie, Xilong Wang, Liang Xiao, Limin et al.

Quelle: 2025 Design, Automation & Test in Europe Conference (DATE). :1-7

Schlagwörter: FOS: Computer and information sciences, Computer Science - Machine Learning, Hardware Architecture (cs.AR), Computer Science - Hardware Architecture, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2504.19746

Software and Hardware Co-optimization for Deep Learning Algorithms on FPGA

Autoren: Wu, Chen

Schlagwörter: Engineering, CNN, FPGA, GCN, Hardware Acceleration, Quantization

Dateibeschreibung: application/pdf

Zugangs-URL: https://escholarship.org/uc/item/02t771j7
https://escholarship.org/content/qt02t771j7/qt02t771j7.pdf

Feature-Driven Semantic Communication for Efficient Image Transmission.

Autoren: Zhang, Ji Zhang, Ying Ji, Baofeng et al.

Quelle: Entropy; Apr2025, Vol. 27 Issue 4, p369, 23p

Schlagwörter: TELECOMMUNICATION systems, IMAGE transmission, FEATURE extraction, IMAGING systems, BANDWIDTHS, IMAGE reconstruction

Adaptive Quantization as a Device-Algorithm Co-Design Approach to Improve the Performance of In-Memory Unsupervised Learning With SNNs.

Autoren: Shi, Yuhan Huang, Zhisheng Oh, Sangheon et al.

Quelle: IEEE Transactions on Electron Devices. Apr2019, Vol. 66 Issue 4, p1722-1728. 7p.

Schlagwörter: *NONVOLATILE memory, *PHASE change memory, *ARTIFICIAL neural networks, *PULSE modulation, *ALGORITHMS

MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

Autoren: Liu, Wenyuan Meng, Haoqian Luo, Yilun et al.

Schlagwörter: Machine Learning, FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Artificial Intelligence, Machine Learning (cs.LG)

Zugangs-URL: http://arxiv.org/abs/2508.02343

Enhancing molecular property prediction with quantized GNN models.

Autoren: Rasool, Areen Ul Rahman, Jamshaid Uwitije, Rongin

Quelle: Journal of Cheminformatics; 5/26/2025, Vol. 17 Issue 1, p1-19, 19p

Schlagwörter: GRAPH neural networks, COMPUTATIONAL chemistry, PHYSICAL & theoretical chemistry, DIPOLE moments, PREDICTION models