Quantized Auto Encoder-Based Anomaly Detection for Multivariate Time Series Data in 5G Networks by Giovanni Trappolini, Antonio Purificato, Federico Siciliano, Luigi D'Addona, Anna Maria Spagnolo, Domenico Dato, Fabrizio Silvestri

“…We provide a detailed evaluation of our model across 5G data scenarios, demonstrating its enhanced accuracy and efficiency in anomaly detection compared to existing state-of-the-art methods, with gains of up to 8%.…”
Get full text

TCL: Time-Dependent Clustering Loss for Optimizing Post-Training Feature Map Quantization for Partitioned DNNs by Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Irida Shallari, Silvia Krug, Isaac Sanchez Leal, Mattias O'Nils

“…TCL regularization clusters activations at the partitioning point to align with quantization levels, minimizing quantization error and ensuring accuracy even with extreme low-bitwidth quantization. …”
Get full text

A Dual-Mode Compatible CT ADC With FIR DAC and SB Quantization for DSM and IDSM Operations by Han Yang, Yuqi Wang, Ying Hou, Xiaosong Wang, Yu Liu

“…At the circuit level, a compact and energy-efficient compensation FIR DAC is implemented based on a configurable capacitive passive summation network. …”
Get full text

Enhancing Autism Spectrum Disorder Classification with Lightweight Quantized CNNs and Federated Learning on ABIDE-1 Dataset by Simran Gupta, Md. Rahad Islam Bhuiyan, Sadia Sultana Chowa, Sidratul Montaha, Rashik Rahman, Sk. Tanzir Mehedi, Ziaur Rahman

“…The proposed 1D-CNN is quantized through Quantize Aware Training (QAT). As the quantization method, int8 quantization is utilized, which makes it both robust and lightweight. …”
Get full text

A novel two-dimensional reversible data hiding scheme based on high-efficiency histogram shifting for JPEG images by Ben He, Yi Chen, Yonghui Zhou, Yongrong Wang, Yanli Chen

Get full text

Neural network compression for reinforcement learning tasks by Dmitry A. Ivanov, Denis A. Larionov, Oleg V. Maslennikov, Vladimir V. Voevodin

“…Abstract In real applications of Reinforcement Learning (RL), such as robotics, low latency, energy-efficient and high-throughput inference is very desired. …”
Get full text

Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems by Minghao Wang, Xin Liu, Fang Wang, Yang Liu, Tianshuang Qiu, Minglu Jin

“…This study proposes a spectrum-efficient and fast convergence deep reinforcement learning (DRL)-based resource allocation framework to optimize user grouping and allocation of subchannel and power. …”
Get full text

InMemQK: A Product Quantization Based MatMul Module for Compute-in-Memory Attention Macro by Pengcheng Feng, Yihao Chen, Jinke Yu, Hao Yue, Zhelong Jiang, Yi Xiao, Wan’ang Xiao, Huaxiang Lu, Gang Chen

“…At the software level, InMemQK employs product quantization (PQ) to eliminate data dependencies. At the hardware level, InMemQK integrates energy-efficient time-domain MAC macros for ADC-free computations. …”
Get full text

Digital Spectral Analysis by means of the Method of Averag Modified Periodograms Using Binary-Sign Stochastic Quantization of Signals by V. N. Yakimov

“…The aim of this work was the development of mathematical and algorithmic support, which can increase the computational efficiency of signals digital spectral analysis by this method.The solution to this problem is based on the use of binary-sign stochastic quantization for converting the analyzed signal into a digital code. …”
Get full text

Quantum-Inspired Multi-Scale Object Detection in UAV Imagery: Advancing Ultra-Small Object Accuracy and Efficiency for Real-Time Applications by Muhammad Muzammul, Muhammad Assam, Ayman Qahmash

“…Efficiency optimizations, including structured pruning and quantization, reduced computational load to 30 GFLOPS with an inference time of 8.1 milliseconds, ensuring suitability for real-time UAV applications on resource-constrained platforms. …”
Get full text

A dynamic simulation method of urban rail traction power supply system based on quantized state time discretization by SHI Xiangwen, LIN Fei, WANG Chao, WU Xiaobo, SHA Donglei, YANG Zhongping

“…The results show that the quantized state time discretization hybrid solution method is feasible, accurate and efficient in the dynamic simulation system of urban rail traction power supply.…”
Get full text

Quantization-Based Jailbreaking Vulnerability Analysis: A Study on Performance and Safety of the Llama3-8B-Instruct Model by Jaesik Lee

“…This study systematically investigates how quantization, a key technique for the efficient deployment of large language models (LLMs), affects model safety. …”
Get full text

A KWS System for Edge-Computing Applications with Analog-Based Feature Extraction and Learned Step Size Quantized Classifier by Yukai Shen, Binyi Wu, Dietmar Straeussnigg, Eric Gutierrez

“…The filter bank is behaviorally modeled, making use of second-order band-pass transfer functions, simulating the analog front-end (AFE) processing. To enable efficient deployment, the GRU classifier is trained using a Learned Step Size (LSQ) and Look-Up Table (LUT)-aware quantization method. …”
Get full text

Deployable Deep Learning for Cross-Domain Plant Leaf Disease Detection via Ensemble Learning, Knowledge Distillation, and Quantization by Mohammad Junayed Hasan, Suvodeep Mazumdar, Sifat Momen

“…Our four-model ensemble (DenseNet-121, ResNet-101, DenseNet-201, EfficientNet-B4) achieves 99.15% accuracy via soft-voting. …”
Get full text

High-Throughput Adaptive Co-Channel Interference Cancellation for Edge Devices Using Depthwise Separable Convolutions, Quantization, and Pruning by Mostafa Naseri, Eli De Poorter, Ingrid Moerman, H. Vincent Poor, Adnan Shahid

“…Our approach is established on architectural modifications, notably through quantization and the incorporation of depthwise separable convolution, to achieve a balance between computational efficiency and performance. …”
Get full text

Highly Efficient Digitized Quasi-3D Photolithography Based on a Modified Golomb Coding via DMD Laser Direct Writing by Hui Wang, Zhe Huang, Yanting Shen, Shangying Zhou

Get full text

Secret Key Generation Driven by Attention-Based Convolutional Autoencoder and Quantile Quantization for IoT Security in 5G and Beyond by Anas Alashqar, Ehsan Olyaei Torshizi, Raed Mesleh, Werner Henkel

“…Specifically, a two-dimensional convolutional neural network–based autoencoder (2D CNN–AE) with a spatial self-attention (SSA) mechanism is developed to efficiently extract and learn channel reciprocity features in time-division duplex (TDD)-based fifth-generation (5G) networks. …”
Get full text

Lightweight faster R-CNN for object detection in optical remote sensing images by Andrew Magdy, Marwa S. Moustafa, Hala M. Ebied, Mohamed F. Tolba

“…First, aware training employs mixed-precision FP16 computation, which enhances training speed by a factor of 1.5 to 5.5 while preserving model accuracy and optimizing memory efficiency. Second, post-training compression applies unstructured weight pruning to eliminate redundant parameters, followed by dynamic quantization to reduce precision, thereby minimizing the model size at runtime and computational load. …”
Get full text

Probing the Pitfalls: Understanding SVD’s Shortcomings in Language Model Compression by Сергей Александрович Плетенев

Get full text

Low-Resolution Quantized Precoding for Multiple-Input Multiple-Output Dual-Functional Radar–Communication Systems Used for Target Sensing by Xiang Feng, Zhongqing Zhao, Jiongshi Wang, Jian Wang, Zhanfeng Zhao, Zhiquan Zhou

“…Furthermore, we propose a dynamic projection refinement algorithm within the alternating direction method of multiplier framework to efficiently solve these sub-problems. Numerical experiments demonstrate that our proposed method outperforms existing state-of-the-art techniques, particularly in terms of bit error rate in low signal-to-noise ratio scenarios.…”
Get full text