Skip to Content

781 Results Found

  • Article
  • Open Access
4 Citations
3,331 Views
12 Pages

2 November 2023

In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges. First...

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing II)
  • Article
  • Open Access
3,002 Views
21 Pages

12 December 2023

Deep neural network quantization is a widely used method in the deployment of mobile or edge devices to effectively reduce memory overhead and speed up inference. However, quantization inevitably leads to a reduction in the performance and equivalenc...

(This article belongs to the Section Artificial Intelligence)
  • Review
  • Open Access
98 Citations
25,920 Views
14 Pages

23 August 2024

Artificial intelligence technologies based on deep convolutional neural networks and large language models have made significant breakthroughs in many tasks, such as image recognition, target detection, semantic segmentation, and natural language pro...

(This article belongs to the Special Issue Advances and Applications of Numerical Analysis and Intelligent Computing)
  • Article
  • Open Access
9 Citations
8,095 Views
22 Pages

4.6-Bit Quantization for Fast and Accurate Neural Network Inference on CPUs

  • Anton Trusov,
  • Elena Limonova,
  • Dmitry Nikolaev and
  • Vladimir V. Arlazarov

23 February 2024

Quantization is a widespread method for reducing the inference time of neural networks on mobile Central Processing Units (CPUs). Eight-bit quantized networks demonstrate similarly high quality as full precision models and perfectly fit the hardware...

(This article belongs to the Special Issue Application of Machine Learning in Image Processing and Computer Vision)
  • Article
  • Open Access
3 Citations
4,277 Views
16 Pages

4 January 2023

Current edge devices for neural networks such as FPGA, CPLD, and ASIC can support low bit-width computing to improve the execution latency and energy efficiency, but traditional linear quantization can only maintain the inference accuracy of neural n...

  • Article
  • Open Access
18 Citations
5,278 Views
12 Pages

NICE: Noise Injection and Clamping Estimation for Neural Network Quantization

  • Chaim Baskin,
  • Evgenii Zheltonozhkii,
  • Tal Rozen,
  • Natan Liss and ,
  • Yoav Chai,
  • Eli Schwartz,
  • Raja Giryes,
  • Alexander M. Bronstein and
  • Avi Mendelson
  • + 4 authors+ 0 author

2 September 2021

Convolutional Neural Networks (CNNs) are very popular in many fields including computer vision, speech recognition, natural language processing, etc. Though deep learning leads to groundbreaking performance in those domains, the networks used are ver...

(This article belongs to the Special Issue Computational Optimizations for Machine Learning)
  • Article
  • Open Access
3 Citations
2,656 Views
23 Pages

29 May 2024

Block compressed sensing (BCS) is a promising method for resource-constrained image/video coding applications. However, the quantization of BCS measurements has posed a challenge, leading to significant quantization errors and encoding redundancy. In...

(This article belongs to the Special Issue Information Theory and Coding for Image/Video Processing)
  • Article
  • Open Access
9 Citations
4,744 Views
15 Pages

7 September 2023

Machine learning deployment on edge devices has faced challenges such as computational costs and privacy issues. Membership inference attack (MIA) refers to the attack where the adversary aims to infer whether a data sample belongs to the training se...

(This article belongs to the Special Issue Security of Sensor Network Systems and Circuits from a Hardware Perspective)
  • Article
  • Open Access
1 Citations
740 Views
33 Pages

9 July 2026

Compared with traditional artificial neural networks (ANNs), spiking neural networks (SNNs) have lower computational complexity, lower energy consumption, and faster inference speed, making them more promising for practical deployment on edge devices...

(This article belongs to the Topic State-of-the-Art Object Detection, Tracking, and Recognition Techniques)
  • Article
  • Open Access
4 Citations
2,336 Views
23 Pages

18 September 2025

With the increasing demand for implementing deep-learning models on devices on resource-constrained devices, the development of power-efficient neural networks has become imperative. This paper introduces HADQ-Net, a novel framework for optimizing de...

  • Article
  • Open Access
4 Citations
4,848 Views
16 Pages

Design of Neural Network Quantizers for Networked Control Systems

  • Juan Esteban Rodriguez Ramirez and
  • Yuki Minami

Nowadays, networked control systems (NCSs) are being widely implemented in many applications. However, several problems negatively affect and compromise the design of practical NCSs. One of them is the performance degradation of the system due to qua...

(This article belongs to the Section Networks)
  • Article
  • Open Access
101 Views
21 Pages

31 October 2026

This paper investigates the event-triggered robust dissipative filtering problem for discrete-time networked nonlinear systems subject to dynamic quantization and stochastic cyber attacks. The networked nonlinear system under consideration is represe...

(This article belongs to the Section E2: Control Theory and Mechanics)
  • Article
  • Open Access
3 Citations
4,112 Views
16 Pages

Quantized Graph Neural Networks for Image Classification

  • Xinbiao Xu,
  • Liyan Ma,
  • Tieyong Zeng and
  • Qinghua Huang

11 December 2023

Researchers have resorted to model quantization to compress and accelerate graph neural networks (GNNs). Nevertheless, several challenges remain: (1) quantization functions overlook outliers in the distribution, leading to increased quantization erro...

(This article belongs to the Special Issue Representation Learning for Computer Vision and Pattern Recognition)
  • Article
  • Open Access
39 Citations
11,819 Views
13 Pages

23 June 2019

Convolutional neural networks (CNN) have achieved excellent results in the field of image recognition that classifies objects in images. A typical CNN consists of a deep architecture that uses a large number of weights and layers to achieve high perf...

(This article belongs to the Special Issue Advances in Deep Learning)
  • Article
  • Open Access
2,172 Views
20 Pages

24 February 2025

Quantization plays a crucial role in deploying neural network models on resource-limited hardware. However, current quantization methods have issues like the large accuracy loss and poor generalization for complex tasks. These issues pose obstacles t...

(This article belongs to the Special Issue Computational Methods and Algorithms for Multimedia Data Analysis and Security)
  • Article
  • Open Access
9 Citations
5,656 Views
25 Pages

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

  • Bassam J. Mohd,
  • Khalil M. Ahmad Yousef,
  • Anas AlMajali and
  • Thaier Hayajneh

Convolutional neural networks (CNNs) have demonstrated remarkable performance in many areas but require significant computation and storage resources. Quantization is an effective method to reduce CNN complexity and implementation. The main research...

(This article belongs to the Special Issue FPGA-Based Deep Neural Network Accelerators Using Emerging Technologies)
  • Article
  • Open Access
8,081 Views
15 Pages

29 June 2010

This paper is concerned with networked estimation, where sensor data are transmitted over a network of limited transmission rate. The transmission rate depends on the sampling periods and the quantization bit lengths. To investigate how the sampling...

(This article belongs to the Special Issue Intelligent Sensors - 2010)
  • Article
  • Open Access
11 Citations
4,436 Views
17 Pages

Design of a 2-Bit Neural Network Quantizer for Laplacian Source

  • Zoran Perić,
  • Milan Savić,
  • Nikola Simić,
  • Bojan Denić and
  • Vladimir Despotović

22 July 2021

Achieving real-time inference is one of the major issues in contemporary neural network applications, as complex algorithms are frequently being deployed to mobile devices that have constrained storage and computing power. Moving from a full-precisio...

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing)
  • Article
  • Open Access
4 Citations
4,323 Views
15 Pages

Network quantization becomes a crucial step when deploying deep models to the edge devices as it is hardware-friendly, offers memory and computational advantages, but it also suffers performance degradation as the result of limited representation cap...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
30 Citations
4,579 Views
16 Pages

An Efficient Classification of Rice Variety with Quantized Neural Networks

  • Mustafa Tasci,
  • Ayhan Istanbullu,
  • Selahattin Kosunalp,
  • Teodor Iliev and ,
  • Ivaylo Stoyanov and
  • Ivan Beloev
  • + 1 author+ 0 author

Rice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a part...

(This article belongs to the Special Issue Application of Artificial Intelligence in the New Era of Communication Networks)
  • Article
  • Open Access
1 Citations
1,764 Views
21 Pages

21 February 2025

Deploying deeply quantized neural networks on FPGA devices can be a time-consuming task. This has led to research on tools to automate this procedure, specifically for the case of fast machine learning. This is a specialized field concerned with the...

(This article belongs to the Section Circuit and Signal Processing)
  • Article
  • Open Access
5 Citations
4,174 Views
15 Pages

2 November 2020

Quantization of the weights and activations of a neural network is a way to drastically reduce necessary memory accesses and to replace arithmetic operations with bit-wise operations. This is especially beneficial for the implementation on field-prog...

(This article belongs to the Section Computer Science & Engineering)
  • Feature Paper
  • Article
  • Open Access
7 Citations
2,587 Views
17 Pages

13 November 2021

Backstepping method is a successful approach to deal with the systems in strict-feedback form. However, for networked control systems, the discontinuous virtual law caused by state quantization introduces huge challenges for its applicability. In thi...

(This article belongs to the Section Systems & Control Engineering)
  • Article
  • Open Access
6 Citations
2,822 Views
26 Pages

Q-A2NN: Quantized All-Adder Neural Networks for Onboard Remote Sensing Scene Classification

  • Ning Zhang,
  • He Chen,
  • Liang Chen,
  • Jue Wang and ,
  • Guoqing Wang and
  • Wenchao Liu
  • + 1 author+ 0 author

30 June 2024

Performing remote sensing scene classification (RSSC) directly on satellites can alleviate data downlink burdens and reduce latency. Compared to convolutional neural networks (CNNs), the all-adder neural network (A2NN) is a novel basic neural network...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
5 Citations
3,258 Views
16 Pages

We propose a neural-network-based watermarking method that introduces the quantized activation function that approximates the quantization of JPEG compression. Many neural-network-based watermarking methods have been proposed. Conventional methods ha...

(This article belongs to the Special Issue Robust Deep Learning Techniques for Multimedia Forensics and Security)
  • Article
  • Open Access
12 Citations
9,017 Views
13 Pages

The Impact of 8- and 4-Bit Quantization on the Accuracy and Silicon Area Footprint of Tiny Neural Networks

  • Paweł Tumialis,
  • Marcel Skierkowski,
  • Jakub Przychodny and
  • Paweł Obszarski

In the field of embedded and edge devices, efforts have been made to make deep neural network models smaller due to the limited size of the available memory and the low computational efficiency. Typical model footprints are under 100 KB. However, for...

  • Systematic Review
  • Open Access
10 Citations
3,763 Views
62 Pages

Quantization of Deep Neural Networks for Medical Image Analysis: A Systematic Review and Meta-Analysis

  • Edgar Fabián Rivera-Guzmán,
  • Luis Fernando Guerrero-Vásquez and
  • Vladimir Espartaco Robles-Bykbaev

Neural network quantization has become established as a key strategy for transitioning medical imaging models from research environments to clinical devices and resource-constrained edge platforms; however, the available evidence remains fragmented a...

(This article belongs to the Special Issue Application of Artificial Intelligence in Medical Image Analysis)
  • Article
  • Open Access
2 Citations
1,586 Views
20 Pages

Efficient Quantization of Pretrained Deep Networks via Adaptive Block Transform Coding

  • Milan Dubljanin,
  • Stefan Panić,
  • Milan Savić,
  • Milan Dejanović and
  • Oliver Popović

12 January 2026

This work investigates the effectiveness of block transform coding (BTC) as a lightweight, training-free quantization strategy for compressing the weights of pretrained deep neural networks. The proposed method applies a rule-based block transform wi...

(This article belongs to the Special Issue Feature Papers in Information in 2024–2025)
  • Article
  • Open Access
38 Citations
6,568 Views
21 Pages

FPGA-Based Hybrid-Type Implementation of Quantized Neural Networks for Remote Sensing Applications

  • Xin Wei,
  • Wenchao Liu,
  • Lei Chen,
  • Long Ma and ,
  • He Chen and
  • Yin Zhuang
  • + 1 author+ 0 author

22 February 2019

Recently, extensive convolutional neural network (CNN)-based methods have been used in remote sensing applications, such as object detection and classification, and have achieved significant improvements in performance. Furthermore, there are a lot o...

(This article belongs to the Section Remote Sensors)
  • Article
  • Open Access
420 Views
34 Pages

Algebraically Stabilizing Blocks for Quantized and Finite-Precision Neural Networks

  • Kostadin Yotov,
  • Emil Hadzhikolev and
  • Stanka Hadzhikoleva

16 July 2026

This paper proposes a construction of algebraically stabilizing blocks for quantized and finite-precision neural networks. The approach is based on linear transformations defined by integer-valued matrices satisfying a condition of the form Wk=I+μ...

(This article belongs to the Special Issue Advances in Linear Algebra with Applications, 2nd Edition)
  • Article
  • Open Access
3 Citations
3,542 Views
17 Pages

4 April 2025

In response to the issue that post-training quantization leads to performance degradation in mobile deployment, as well as the problem that the balanced consideration of quantization deviation by Clipping optimization techniques limits the improvemen...

(This article belongs to the Special Issue Big Data Analysis and Management Based on Deep Learning: 2nd Edition)
  • Article
  • Open Access
1 Citations
1,714 Views
14 Pages

25 August 2023

This brief discusses the use of quantized control with actuator saturation to achieve the local synchronization of master–slave fractional-order neural networks (FONNs). A refined sector condition (RSC) is proposed that addresses the issue of t...

  • Article
  • Open Access
759 Views
21 Pages

25 May 2026

Quantization reduces the precision of neural network parameters to accelerate inference and lower power consumption, but it often causes noticeable accuracy degradation. We propose a differentiable quantization framework that replaces the non-differe...

(This article belongs to the Special Issue Innovations in Artificial Neural Network Applications)
  • Article
  • Open Access
6 Citations
1,841 Views
19 Pages

This article investigates the problem of finite-time synchronization of fractional-order complex-valued random multi-layer networks without decomposing them into two real-valued systems. Firstly, by promoting real-valued signum functions, sign functi...

  • Article
  • Open Access
35 Citations
3,149 Views
25 Pages

VBQ-Net: A Novel Vectorization-Based Boost Quantized Network Model for Maximizing the Security Level of IoT System to Prevent Intrusions

  • Ganeshkumar Perumal,
  • Gopalakrishnan Subburayalu,
  • Qaisar Abbas,
  • Syed Muhammad Naqi and
  • Imran Qureshi

21 August 2023

Data sharing with additional devices across wireless networks is made simple and advantageous by the Internet of Things (IoT), an emerging technology. However, IoT systems are more susceptible to cyberattacks because of their continued growth and tec...

  • Article
  • Open Access
4 Citations
3,317 Views
15 Pages

Deep convolutional neural networks have a large number of parameters and require a significant number of floating-point operations during computation, which limits their deployment in situations where the storage space is limited and computational re...

(This article belongs to the Special Issue Deep Learning-Based Image Restoration and Object Identification)
  • Article
  • Open Access
945 Views
28 Pages

16 June 2025

This paper investigates the event-triggered dissipative fuzzy tracking control problem of nonlinear networked systems with dynamic quantization and stochastic deception attacks, where the Takagi–Sugeno (T-S) fuzzy system theory is utilized to r...

(This article belongs to the Special Issue Stability and Optimal Control of Linear Systems)
  • Article
  • Open Access
35 Citations
7,924 Views
19 Pages

A Case Study of Quantizing Convolutional Neural Networks for Fast Disease Diagnosis on Portable Medical Devices

  • Mukhammed Garifulla,
  • Juncheol Shin,
  • Chanho Kim,
  • Won Hwa Kim and ,
  • Hye Jung Kim,
  • Jaeil Kim and
  • Seokin Hong
  • + 2 authors+ 0 author

29 December 2021

Recently, the amount of attention paid towards convolutional neural networks (CNN) in medical image analysis has rapidly increased since they can analyze and classify images faster and more accurately than human abilities. As a result, CNNs are becom...

(This article belongs to the Special Issue Advanced Machine Learning Techniques for Biomedical Imaging Sensing and Healthcare Applications)
  • Article
  • Open Access
8 Citations
2,193 Views
24 Pages

This paper is devoted to investigating the synchronization of fractional-order output-coupling multiplex networks (FOOCMNs). Firstly, a type of fractional-order multiplex network is introduced, where the intra-layer coupling and the inter-layer coupl...

(This article belongs to the Special Issue Recent Advances in Fractional-Order Neural Networks: Theory and Application)
  • Article
  • Open Access
9 Citations
4,801 Views
14 Pages

Pattern Classification Using Quantized Neural Networks for FPGA-Based Low-Power IoT Devices

  • Manas Ranjan Biswal,
  • Tahesin Samira Delwar,
  • Abrar Siddique,
  • Prangyadarsini Behera and ,
  • Yeji Choi and
  • Jee-Youl Ryu
  • + 1 author+ 0 author

10 November 2022

With the recent growth of the Internet of Things (IoT) and the demand for faster computation, quantized neural networks (QNNs) or QNN-enabled IoT can offer better performance than conventional convolution neural networks (CNNs). With the aim of reduc...

(This article belongs to the Topic Applications in Image Analysis and Pattern Recognition)
  • Article
  • Open Access
1 Citations
3,423 Views
16 Pages

20 February 2023

Existing secure multiparty computation protocol from secret sharing is usually under this assumption of the fast network, which limits the practicality of the scheme on the low bandwidth and high latency network. A proven method is to reduce the comm...

(This article belongs to the Special Issue Information Theory for Distributed Systems)
  • Article
  • Open Access
4 Citations
1,910 Views
20 Pages

23 February 2023

This paper investigates the observer-based non-fragile output feedback tracking control problem for nonlinear networked systems with randomly occurring gain variations. The considered nonlinear networked systems are represented by a Takagi–Suge...

(This article belongs to the Special Issue Analysis and Control of Dynamical Systems)
  • Article
  • Open Access
2 Citations
2,235 Views
20 Pages

Distributed Estimation of Fields Using a Sensor Network with Quantized Measurements

  • Chethaka Jayasekaramudeli,
  • Alex S. Leong,
  • Alexei T. Skvortsov,
  • David J. Nielsen and
  • Omar Ilaya

15 August 2024

In this paper, the problem of estimating a scalar field (e.g., the spatial distribution of contaminants in an area) using a sensor network is considered. The sensors are assumed to have quantized measurements. We consider distributed estimation algor...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
870 Views
33 Pages

11 June 2026

Wearable ECG monitors enable continuous cardiac surveillance, but most still rely on cloud-based analysis with limited on-device support for multi-class arrhythmia detection. Spiking neural networks (SNNs) are promising for low-power edge inference,...

(This article belongs to the Section Biomedical Sensors)
  • Article
  • Open Access
445 Views
17 Pages

Adaptive A-Semilogarithmic Gradient Quantization for Efficient Deep Neural Network Training

  • Stefan Panić,
  • Milan Dubljanin,
  • Milan Savić and
  • Marko Smilić

29 June 2026

This paper introduces an adaptive A-semilogarithmic gradient quantization framework aimed at reducing memory overhead and computational complexity during the training of deep neural networks. The approach employs a semilogarithmic companding function...

(This article belongs to the Special Issue Deep Neural Networks and Optimization Algorithms (2nd Edition))
  • Article
  • Open Access
3 Citations
3,641 Views
32 Pages

15 February 2024

The Large Hadron Collider (LHC) is being prepared for an extensive upgrade to boost its particle discovery potential. The new phase, High Luminosity LHC, will operate at a factor-of-five-increased luminosity (the number proportional to the rate of co...

  • Article
  • Open Access
9 Citations
2,686 Views
14 Pages

30 November 2021

This paper considers the fixed-time synchronization (FIXTS) of neural networks (NNs) by using quantized intermittent control (QIC). Based on QIC, a fixed-time controller is designed to ensure that the NNs achieve synchronization in finite time. With...

(This article belongs to the Special Issue Modeling and Analysis of Complex Networks)
  • Article
  • Open Access
687 Views
21 Pages

Bipartite Synchronization for Signed Luré Networks via Semi-Markovian Jump Switching and Quantized Pinning Control

  • Suresh Rasappan,
  • Sathish Kumar Kumaravel,
  • Regan Murugesan,
  • Wardah Abdullah Al Majrafi and
  • Pugalarasu Rajan

1 February 2026

This paper investigates bipartite synchronization in signed Lur’e networks influenced by semi-Markovian jump dynamics. A control strategy is proposed that adapts to mode-dependent switching by combining quantized feedback with selective pinning...

(This article belongs to the Section Electrical and Electronic Engineering)
  • Article
  • Open Access
7 Citations
2,239 Views
20 Pages

1 June 2023

In this paper, the design of a dynamic output feedback controller for a networked control system with dual-channel data packet loss and special discrete-time delay is studied, in which the data packet loss is described by the Markov process. In order...

(This article belongs to the Section C2: Dynamical Systems)
  • Article
  • Open Access
830 Views
38 Pages

19 November 2025

This study addresses the preassigned-time (PDT) projective lag synchronization of octonion-valued BAM neural networks (OV-BAMNNs) through exponential quantized event-triggered control (ETC). First, an OV-BAMNN model incorporating discontinuous activa...

of 16