The development of hardware-based cognitive computing systems critically hinges upon the integration of memristor devices capable of versatile weight expression across a spectrum of resistance levels while preserving consistent electrical properties....
Using Spatial Domain Correlation Pattern Recognition (CPR) in Internet-of-Things (IoT)-based applications often faces constraints, like inadequate computational resources and limited memory. To reduce the computation workload of inference due to larg...
Network quantization, which strives to reduce the precision of model parameters and/or features, is one of the most efficient ways to accelerate model inference and reduce memory consumption, particularly for deep models when performing a variety of...
Image steganalysis methods aim at detecting whether there exist hidden messages in images. Deep learning (DL) models have been proposed to enhance steganography detection. These models occupy a large amount of memory and, for this reason, should be o...
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...
A new stepwise and radially processed method for synthesizing uniformly distributed circular planar arrays with quantized weights is proposed in this paper. This method is based on a generalized analytical equation describing that for high directivit...
A hardware-based spiking neural network (SNN) has attracted many researcher’s attention due to its energy-efficiency. When implementing the hardware-based SNN, offline training is most commonly used by which trained weights by a software-based artifi...
Many quantum systems admit an explicit analytic Fourier space expansion, besides the usual analytic Schrödinger configuration space representation. We argue that the use of weighted orthonormal polynomial expansions for the physical states (generated...
With the rapid development of artificial intelligence (AI) theory, particularly deep learning neural networks, robot vacuums equipped with AI power can automatically clean indoor floors by using intelligent programming and vacuuming services. To date...
Large language model (LLM) inference is an increasing component of AI energy demand, while the energy effects of weight quantization depend on workload phase and implementation. We benchmarked four LLM families—Gemma 4 E4B IT, Qwen3.5 4B, Nemot...
Insect bites are a common cause of skin irritation and can contribute to disease transmission through vector-borne pathogens. Early identification of the likely biting organism can assist preliminary guidance (e.g., monitoring for warning signs, cons...
Blockwise reconstruction with adaptive rounding helps achieve acceptable 4-bit post-training quantization accuracy. However, adaptive rounding is time intensive, and the optimization space of weight elements is constrained to a binary set, thus limit...
Artificial intelligence (AI) plays a critical role in the operation of robot vacuum cleaners, enabling them to intelligently navigate to clean and avoid indoor obstacles. Due to limited computational resources, manufacturers must balance performance...
This paper proposes a novel and efficient low-complexity chromatic dispersion equalizer (CDE) based on finite impulse response (FIR) filter architecture for polarization-multiplexed coherent optical communication systems. The FIR filter coefficients...
Spiking neural networks (SNN) increasingly attract attention for their similarity to the biological neural system. Hardware implementation of spiking neural networks, however, remains a great challenge due to their excessive complexity and circuit si...
Multimodal Emotion Recognition in Conversation (ERC) has attracted attention as a key technology in human–computer interaction, mental healthcare, and intelligent services. However, deploying ERC in real-world settings remains challenging due t...
Quantization of neural networks has been one of the most popular techniques to compress models for embedded (IoT) hardware platforms with highly constrained latency, storage, memory-bandwidth, and energy specifications. Limiting the number of bits pe...
Source number estimation plays an important role in successful blind signal separation. At present, the application of machine learning allows the processing of signals without the time-consuming and complex work of manual feature extraction. However...
Intelligent sensing systems are increasingly used in wearable devices, enabling advanced tasks across various application domains including robotics and human–machine interaction. Ensuring these systems are energy autonomous is highly demanded,...
Robot vacuum cleaners have gained widespread popularity as household appliances. One significant challenge in enhancing their functionality is to identify and classify small indoor objects suitable for safe suctioning and recycling during cleaning op...
Although optimizing deep neural networks is becoming crucial for deploying the networks on edge AI devices, it faces increasing challenges due to scarce hardware resources in modern IoT and mobile devices. This study proposes a quantization method th...
The workloads of Convolutional Neural Networks (CNNs) exhibit a streaming nature that makes them attractive for reconfigurable architectures such as the Field-Programmable Gate Arrays (FPGAs), while their increased need for low-power and speed has es...
Convolutional Neural Networks (CNNs) are popular models that are widely used in image classification, target recognition, and other fields. Model compression is a common step in transplanting neural networks into embedded devices, and it is often use...
The use of advanced modulation and control schemes for power converters, such as a Feedback Quantizer and Predictive Control, is widely studied in the literature. This work focuses on improving the closed-loop modulation scheme called Feedback Quanti...
YOLO (You Only Look Once) has become the dominant paradigm in real-time object detection. However, deploying real-time object detectors on resource-constrained platforms faces challenges due to high computational and memory demands. Quantization addr...
With the rapid growth of sensor technology and computer vision, efficient deep learning models are essential for real-time image feature extraction in resource-constrained environments. However, most existing quantized deep neural networks (DNNs) are...
Integral quantization is a powerful framework for mapping classical phase-space functions—defined on a symplectic manifold—onto quantum operators in a Hilbert space. It encompasses several quantization methods, such as coherent-state quan...
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 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...
In the field of edge computing, quantizing convolutional neural networks (CNNs) using extremely low bit widths can significantly alleviate the associated storage and computational burdens in embedded hardware, thereby improving computational efficien...
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...
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...
Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the...
Extensive research on deep neural networks for LiDAR point clouds has contributed inexhaustible momentum to the development of computer 3D vision applications. However, storage and energy consumption have always been a challenge for deploying these d...
A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented that investigate the effect...
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...
Vision–language models (VLMs) are increasingly deployed in resource-constrained environments, yet efficient fine-tuning remains challenging because post-training quantization often degrades the effectiveness of low-rank adaptation. This paper r...
Modern large language models (LLMs) achieve state-of-the-art performance through architectural advancements but require high computational costs for inference. Post-training quantization is a widely adopted approach to reduce these costs by quantizin...
In this paper, a parameter optimal gain-arguable iterative learning control algorithm is proposed for a class of linear discrete-time systems with quantized error. Based on the lifting model description for ILC systems, the iteration time-variable de...
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...
To address the problems of convolutional neural networks (CNNs) consuming more hardware resources (such as DSPs and RAMs on FPGAs) and their accuracy, efficiency, and resources being difficult to balance, meaning they cannot meet the requirements of...
Motivated by the fact that uniform quantization is not suitable for signals having non-uniform probability density functions (pdfs), as the Laplacian pdf is, in this paper we have divided the support region of the quantizer into two disjunctive regio...
A control strategy for a certain class of hypersonic flight aircraft dynamic models with unknown parameters is proposed in this article. The strategy is adaptive dynamic surface input quantization control. To address the issues in conventional invers...
Binarization is an extreme quantization technique that is attracting research in the Internet of Things (IoT) field, as it radically reduces the memory footprint of deep neural networks without a correspondingly significant accuracy drop. To support...
Pruning and quantization are two commonly used approaches to accelerate the LSTM (Long Short-Term Memory) model. However, the traditional linear quantization usually suffers from the problem of gradient vanishing, and the existing pruning methods all...
Convolutional neural network (CNN)-based synthetic aperture radar (SAR) ship detection models operating directly on satellites can reduce transmission latency and improve real-time surveillance capabilities. However, limited satellite platform resour...
Although neural network quantization is an imperative technology for the computation and memory efficiency of embedded neural network accelerators, simple post-training quantization incurs unacceptable levels of accuracy degradation on some important...
Speckle noise seriously affects synthetic aperture radar (SAR) image application. Speckle suppression aims to smooth the homogenous region while preserving edge and texture in the image. A novel speckle suppression method based on the combination of...
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 study introduces an innovative approach aimed at enhancing the accuracy of attitude determination through the computation of star observation quality. The proposed algorithm stems from the inherent invariance of singular values under attitude tr...
of 6