Skip to Content
You are currently on the new version of our website. Access the old version .

749 Results Found

  • Article
  • Open Access
27 Citations
3,909 Views
11 Pages

27 April 2023

Recently, there has been a rapid increase in deep classification tasks, such as image recognition and target detection. As one of the most crucial components in Convolutional Neural Network (CNN) architectures, softmax arguably encourages CNN to achi...

  • Article
  • Open Access
7 Citations
5,492 Views
11 Pages

Double Additive Margin Softmax Loss for Face Recognition

  • Shengwei Zhou,
  • Caikou Chen,
  • Guojiang Han and
  • Xielian Hou

19 December 2019

Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line...

(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
  • Article
  • Open Access
37 Citations
16,526 Views
20 Pages

In this paper a simplified hardware implementation of a CNN softmax-like layer is proposed. Initially the softmax activation function is analyzed in terms of required numerical accuracy and certain optimizations are proposed. A proposed adaptable har...

(This article belongs to the Special Issue MOCAST 2019: Modern Circuits and Systems Technologies on Electronics)
  • Article
  • Open Access
17 Citations
4,903 Views
20 Pages

A Partially Interpretable Adaptive Softmax Regression for Credit Scoring

  • Lkhagvadorj Munkhdalai,
  • Keun Ho Ryu,
  • Oyun-Erdene Namsrai and
  • Nipon Theera-Umpon

3 April 2021

Credit scoring is a process of determining whether a borrower is successful or unsuccessful in repaying a loan using borrowers’ qualitative and quantitative characteristics. In recent years, machine learning algorithms have become widely studied in t...

(This article belongs to the Special Issue Data Technology Applications in Life, Diseases, and Health)
  • Article
  • Open Access
5 Citations
2,191 Views
13 Pages

Residual and Past Discrete Tsallis and Renyi Extropy with an Application to Softmax Function

  • Taghreed M. Jawa,
  • Nahid Fatima,
  • Neveen Sayed-Ahmed,
  • Ramy Aldallal and
  • Mohamed Said Mohamed

27 November 2022

In this paper, based on the discrete lifetime distribution, the residual and past of the Tsallis and Renyi extropy are introduced as new measures of information. Moreover, some of their properties and their relation to other measures are discussed. F...

(This article belongs to the Special Issue Rényi Entropy: Sixty Years Later)
  • Article
  • Open Access
4 Citations
2,528 Views
24 Pages

7 January 2026

With the rapid advancement of Transformer-based large language models (LLMs), these models have found widespread applications in industrial domains such as code generation and non-functional requirement (NFR) classification in software engineering. H...

(This article belongs to the Special Issue Advances in Field-Programmable Gate Arrays (FPGAs))
  • Article
  • Open Access
8 Citations
2,543 Views
11 Pages

Hybrid-Margin Softmax for the Detection of Trademark Image Similarity

  • Chenyang Wang,
  • Guangyuan Zheng and
  • Hongtao Shan

28 March 2024

The detection of image similarity is critical to trademark (TM) legal registration and court judgment on infringement cases. Meanwhile, there are great challenges regarding the annotation of similar pairs and model generalization on rapidly growing d...

(This article belongs to the Topic Computer Vision and Image Processing, 2nd Edition)
  • Article
  • Open Access
1 Citations
958 Views
18 Pages

Softmax is a step in transformer computation during which the internal buffer size grows rapidly because of the use of the exponential function. Softmax is a fundamental yet computationally expensive operation in vision transformer attention, posing...

  • Letter
  • Open Access
10 Citations
3,950 Views
17 Pages

16 August 2020

Internet of Things (IoT) devices bring us rich sensor data, such as images capturing the environment. One prominent approach to understanding and utilizing such data is image classification which can be effectively solved by deep learning (DL). Combi...

(This article belongs to the Special Issue Intelligent Sensors for Positioning, Tracking, Monitoring, Navigation and Smart Sensing in Smart Cities)
  • Article
  • Open Access
5 Citations
3,258 Views
21 Pages

8 May 2022

With the development and popularization of unmanned aerial vehicles (UAVs) and surveillance cameras, vehicle re-identification (ReID) task plays an important role in the field of urban safety. The biggest challenge in the field of vehicle ReID is how...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
14 Citations
5,553 Views
11 Pages

A Low-Voltage, Low-Power Reconfigurable Current-Mode Softmax Circuit for Analog Neural Networks

  • Massimo Vatalaro,
  • Tatiana Moposita,
  • Sebastiano Strangio,
  • Lionel Trojman and ,
  • Andrei Vladimirescu,
  • Marco Lanuzza and
  • Felice Crupi
  • + 2 authors+ 0 author

This paper presents a novel low-power low-voltage analog implementation of the softmax function, with electrically adjustable amplitude and slope parameters. We propose a modular design, which can be scaled by the number of inputs (and of correspondi...

(This article belongs to the Special Issue Design of Ultra-Low Voltage/Power Circuits and Systems)
  • Article
  • Open Access
2 Citations
8,378 Views
12 Pages

Personalized Online Live Video Streaming Using Softmax-Based Multinomial Classification

  • Kyeongseon Kim,
  • Dohyun Kwon,
  • Joongheon Kim and
  • Aziz Mohaisen

4 June 2019

As the demand for over-the-top and online streaming services exponentially increases, many techniques for Quality of Experience (QoE) provisioning have been studied. Users can take actions (e.g., skipping) while streaming a video. Therefore, we shoul...

(This article belongs to the Special Issue Actionable Pattern-Driven Analytics and Prediction)
  • Article
  • Open Access
1 Citations
1,918 Views
31 Pages

Low-power NPUs enable on-device LLM inference through efficient integer and fixed-point algebra, yet their lack of native exponential support makes Transformer softmax a critical performance bottleneck. Existing NPU kernels approximate ex using unifo...

(This article belongs to the Special Issue Emerging Applications of FPGAs and Reconfigurable Computing System)
  • Article
  • Open Access
55 Citations
5,029 Views
13 Pages

20 November 2020

In recent times, several machine learning models have been built to aid in the prediction of diverse diseases and to minimize diagnostic errors made by clinicians. However, since most medical datasets seem to be imbalanced, conventional machine learn...

(This article belongs to the Special Issue Computational Intelligence in Healthcare)
  • Article
  • Open Access
5 Citations
4,583 Views
16 Pages

6 April 2023

Recently, the performance of end-to-end speech recognition has been further improved based on the proposed Conformer framework, which has also been widely used in the field of speech recognition. However, the Conformer model is mostly applied to very...

(This article belongs to the Section Acoustics and Vibrations)
  • Article
  • Open Access
47 Citations
4,694 Views
13 Pages

17 February 2019

The development and application of marine current energy are attracting more and more attention around the world. Due to the hardness of its working environment, it is important and difficult to study the fault diagnosis of a marine current generatio...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
390 Views
26 Pages

16 July 2026

The distributed policy gradient (PG) method has become a mainstream technique for finding optimal policies in multi-agent reinforcement learning. However, global convergence guarantees, which are the most basic measures of theoretical convergence per...

(This article belongs to the Special Issue Advances in Artificial Intelligence: Models, Optimization, and Machine Learning, 3rd Edition)
  • Article
  • Open Access
7 Citations
3,776 Views
18 Pages

Reducing Q-Value Estimation Bias via Mutual Estimation and Softmax Operation in MADRL

  • Zheng Li,
  • Xinkai Chen,
  • Jiaqing Fu,
  • Ning Xie and
  • Tingting Zhao

16 January 2024

With the development of electronic game technology, the content of electronic games presents a larger number of units, richer unit attributes, more complex game mechanisms, and more diverse team strategies. Multi-agent deep reinforcement learning shi...

(This article belongs to the Special Issue Algorithms for Games AI)
  • Article
  • Open Access
11 Citations
4,698 Views
18 Pages

1 October 2023

The deep learning technique has already been successfully applied in the field of microwave remote sensing. Especially, convolutional neural networks have demonstrated remarkable effectiveness in synthetic aperture radar (SAR) image semantic segmenta...

(This article belongs to the Special Issue Target Detection with Fully-Polarized Radar)
  • Article
  • Open Access
4 Citations
1,626 Views
17 Pages

11 November 2025

In bearing fault diagnosis for rotating machinery, multi-sensor data—such as acoustic and vibration signals—are increasingly leveraged to enhance diagnostic performance. However, existing methods often rely on complex network architecture...

(This article belongs to the Special Issue Smart Sensors for Machine Condition Monitoring and Fault Diagnosis)
  • Article
  • Open Access
9 Citations
2,775 Views
23 Pages

10 April 2024

To address the issue associated with poor accuracy rates for specific emitter identification (SEI) under low signal-to-noise ratio (SNR) conditions, where the single-dimension radar signal characteristics are severely affected by noise, we propose an...

(This article belongs to the Special Issue Advanced Radar Signal Processing and Applications)
  • Article
  • Open Access
8 Citations
4,471 Views
14 Pages

18 August 2024

Modern aviation security systems are largely tied to the work of screening operators. Due to physical characteristics, they are prone to problems such as fatigue, loss of attention, etc. There are methods for recognizing such objects, but they face s...

(This article belongs to the Section D2: Operations Research and Fuzzy Decision Making)
  • Article
  • Open Access
4 Citations
2,755 Views
20 Pages

The prediction of patient survival is crucial for guiding the treatment process in healthcare. Healthcare professionals rely on analyzing patients’ clinical characteristics and findings to determine treatment plans, making accurate predictions...

(This article belongs to the Special Issue Biomimetic Approaches in Healthcare—Innovations Inspired by Nature)
  • Article
  • Open Access
14 Citations
5,521 Views
16 Pages

Revisiting Softmax for Uncertainty Approximation in Text Classification

  • Andreas Nugaard Holm,
  • Dustin Wright and
  • Isabelle Augenstein

20 July 2023

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) dropout, which is computationally exp...

(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
  • Article
  • Open Access
17 Citations
10,343 Views
18 Pages

Hardware Accelerator for Approximation-Based Softmax and Layer Normalization in Transformers

  • Raehyeong Kim,
  • Dayoung Lee,
  • Jinyeol Kim,
  • Joungmin Park and
  • Seung Eun Lee

Transformer-based models have achieved remarkable success across various AI tasks, but their growing complexity has led to significant computational and memory demands. While most optimization efforts have focused on linear operations such as matrix...

(This article belongs to the Special Issue Feature Papers in "Computer Science & Engineering", 2nd Edition)
  • Article
  • Open Access
9 Citations
6,857 Views
21 Pages

The study focuses on news category prediction and investigates the performance of sentence embedding of four transformer models (BERT, RoBERTa, MPNet, and T5) and their variants as feature vectors when combined with Softmax and Random Forest using tw...

(This article belongs to the Special Issue Artificial Intelligence Models, Tools and Applications with A Social and Semantic Impact)
  • Article
  • Open Access
2 Citations
3,074 Views
18 Pages

10 October 2022

Adversarial examples easily mislead vision systems based on deep neural networks (DNNs) trained with softmax cross entropy (SCE) loss. The vulnerability of DNN comes from the fact that SCE drives DNNs to fit on the training examples, whereas the resu...

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)
  • Article
  • Open Access
37 Citations
2,242 Views
16 Pages

Enhancing Chinese Dialogue Generation with Word–Phrase Fusion Embedding and Sparse SoftMax Optimization

  • Shenrong Lv,
  • Siyu Lu,
  • Ruiyang Wang,
  • Lirong Yin and ,
  • Zhengtong Yin,
  • Salman A. AlQahtani,
  • Jiawei Tian and
  • Wenfeng Zheng
  • + 3 authors+ 0 author

24 November 2024

Chinese dialogue generation faces multiple challenges, such as semantic understanding, information matching, and response fluency. Generative dialogue systems for Chinese conversation are somehow difficult to construct because of the flexible word or...

(This article belongs to the Section Artificial Intelligence and Digital Systems Engineering)
  • Feature Paper
  • Article
  • Open Access
62 Citations
8,426 Views
8 Pages

24 April 2020

Convolutional neural networks (CNNs) have made great achievements on computer vision tasks, especially the image classification. With the improvement of network structure and loss functions, the performance of image classification is getting higher a...

(This article belongs to the Special Issue Advanced Intelligent Imaging Technology Ⅱ)
  • Article
  • Open Access
8 Citations
4,807 Views
16 Pages

Powered Landing Control of Reusable Rockets Based on Softmax Double DDPG

  • Wenting Li,
  • Xiuhui Zhang,
  • Yunfeng Dong,
  • Yan Lin and
  • Hongjue Li

Multi-stage launch vehicles are currently the primary tool for humans to reach extraterrestrial space. The technology of recovering and reusing rockets can effectively shorten rocket launch cycles and reduce space launch costs. With the development o...

(This article belongs to the Section Astronautics & Space Science)
  • Article
  • Open Access
10 Citations
5,911 Views
15 Pages

28 November 2023

In recent decades, machine-learning algorithms have been extensively utilized to tackle various complex tasks. To achieve the high performance and efficiency of these algorithms, various hardware accelerators are used. Typically, these devices are sp...

(This article belongs to the Special Issue Hardware-Aware Deep Learning)
  • Article
  • Open Access
413 Views
25 Pages

7 July 2026

Brain tumor classification from magnetic resonance imaging (MRI) remains challenging in settings where only image-level labels are available and tumor classes exhibit overlapping visual characteristics. In this study, we consider the publicly availab...

(This article belongs to the Special Issue Evolutionary Algorithms for Engineering Optimization, Fuzzy Control, and Decision Systems)
  • Article
  • Open Access
4 Citations
2,263 Views
18 Pages

20 October 2023

When considering a large dataset of histopathologic breast images captured at various magnification levels, the process of distinguishing between benign and malignant cancer from these images can be time-intensive. The automation of histopathological...

(This article belongs to the Special Issue Medical Applications of Artificial Intelligence)
  • Article
  • Open Access
54 Citations
7,226 Views
19 Pages

Fault Detection and Classification in MMC-HVDC Systems Using Learning Methods

  • Qinghua Wang,
  • Yuexiao Yu,
  • Hosameldin O. A. Ahmed,
  • Mohamed Darwish and
  • Asoke K. Nandi

8 August 2020

In this paper, we explore learning methods to improve the performance of the open-circuit fault diagnosis of modular multilevel converters (MMCs). Two deep learning methods, namely, convolutional neural networks (CNN) and auto encoder based deep neur...

(This article belongs to the Special Issue Deep Learning, Artificial Neural Networks and Sensors for Fault Diagnosis)
  • Article
  • Open Access
359 Views
21 Pages

4 September 2026

On resource-constrained edge hardware, fixed-point Transformer inference is constrained by GEMM kernels and non-GEMM normalization paths. In LayerNorm and Softmax, division, inverse square root, and denominator reciprocal operations complicate fixed-...

(This article belongs to the Special Issue Advanced Technologies in Signal and Image Processing)
  • Article
  • Open Access
63 Citations
7,962 Views
18 Pages

1 September 2022

Cassava is a typical staple food in the tropics, and cassava leaf disease can cause massive yield reductions in cassava, resulting in substantial economic losses and a lack of staple foods. However, the existing convolutional neural network (CNN) for...

(This article belongs to the Topic Applications of Big Data and Machine Learning in Smart Agriculture)
  • Article
  • Open Access
1,606 Views
23 Pages

Brain age has been widely recognized as an important biomarker for monitoring adolescent brain development and assessing dementia risk. However, existing model visualization methods primarily highlight brain regions associated with aging, making it d...

(This article belongs to the Special Issue Image and Signal Processing Techniques and Applications)
  • Article
  • Open Access
3 Citations
2,164 Views
14 Pages

Margin CosReid Network for Pedestrian Re-Identification

  • Xiao Yun,
  • Min Ge,
  • Yanjing Sun,
  • Kaiwen Dong and
  • Xiaofeng Hou

17 February 2021

This paper proposes a margin CosReid network for effective pedestrian re-identification. Aiming to overcome the overfitting, gradient explosion, and loss function non-convergence problems caused by traditional CNNs, the proposed GBNeck model can real...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Feature Paper
  • Article
  • Open Access
58 Citations
7,691 Views
16 Pages

Correlations of Cross-Entropy Loss in Machine Learning

  • Richard Connor,
  • Alan Dearle,
  • Ben Claydon and
  • Lucia Vadicamo

3 June 2024

Cross-entropy loss is crucial in training many deep neural networks. In this context, we show a number of novel and strong correlations among various related divergence functions. In particular, we demonstrate that, in some circumstances, (a) cross-e...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
11 Citations
4,354 Views
18 Pages

Dynamic Graph Learning for Session-Based Recommendation

  • Zhiqiang Pan,
  • Wanyu Chen and
  • Honghui Chen

19 June 2021

Session-based recommendation (SBRS) aims to make recommendations for users merely based on the ongoing session. Existing GNN-based methods achieve satisfactory performance by exploiting the pair-wise item transition pattern; however, they ignore the...

  • Article
  • Open Access
38 Citations
5,991 Views
19 Pages

2 February 2021

Automatic Modulation Classification (AMC) is of paramount importance in wireless communication systems. Existing methods usually adopt a single category of neural network or stack different categories of networks in series, and rarely extract differe...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
2 Citations
3,783 Views
28 Pages

Mixed Structure with 3D Multi-Shortcut-Link Networks for Hyperspectral Image Classification

  • Hui Zheng,
  • Yizhi Cao,
  • Min Sun,
  • Guihai Guo and ,
  • Junzhen Meng,
  • Xinwei Guo and
  • Yanchi Jiang
  • + 2 authors+ 0 author

2 March 2022

A hyperspectral image classification method based on a mixed structure with a 3D multi-shortcut-link network (MSLN) was proposed for the features of few labeled samples, excess noise, and heterogeneous homogeneity of features in hyperspectral images....

(This article belongs to the Topic Artificial Intelligence in Sensors)
  • Article
  • Open Access
2 Citations
1,789 Views
14 Pages

In this study, we propose the CVMFCC-DR (Complex-Valued Mel-Frequency Cepstral Coefficients Dimensionality Reduction) algorithm as an efficient method for reducing the dimensionality of speech signals. By utilizing the complex-valued MFCC technique,...

(This article belongs to the Special Issue Advances in Artificial Intelligence Engineering)
  • Article
  • Open Access
7 Citations
3,192 Views
20 Pages

26 February 2022

Single-sample face recognition is a very challenging problem, where each person has only one labeled training sample. It is difficult to describe unknown facial variations. In this paper, we propose a shared generative adversarial network (SharedGAN)...

(This article belongs to the Special Issue Mathematical Methods in Image Processing and Computer Vision)
  • Article
  • Open Access
6 Citations
4,097 Views
14 Pages

Prediction of pH Value by Multi-Classification in the Weizhou Island Area

  • Haocai Huang,
  • Rendong Feng,
  • Jiang Zhu and
  • Peiliang Li

8 September 2019

Ocean acidification is changing the chemical environment on which marine life depends. It causes a decrease in seawater pH and changes the water quality parameters of seawater. Changes in water quality parameters may affect pH, a key indicator for as...

(This article belongs to the Special Issue Multi-Sensor Fusion and Data Analysis)
  • Article
  • Open Access
1 Citations
515 Views
16 Pages

8 May 2026

Traditional fault diagnosis methods face challenges such as the insufficient utilization of fault information and an imbalance between classification accuracy and computation. To address these issues, a novel multi-source fault diagnosis strategy bas...

(This article belongs to the Section Fault Diagnosis & Sensors)
  • Article
  • Open Access
1 Citations
3,098 Views
13 Pages

Hierarchical Prototypes Polynomial Softmax Loss Function for Visual Classification

  • Chengcheng Xiao,
  • Xiaowen Liu,
  • Chi Sun,
  • Zhongyu Liu and
  • Enjie Ding

13 October 2022

A well-designed loss function can effectively improve the characterization ability of network features without increasing the amount of calculation in the model inference stage, and has become the focus of attention in recent research. Given that the...

  • Article
  • Open Access
1 Citations
2,569 Views
12 Pages

15 September 2021

How to deal with rare and unknown data in traffic classification has a decisive influence on classification performance. Rare data make it difficult to generate validation datasets to prevent overfitting, and unknown data interferes with learning and...

(This article belongs to the Section Computer Science & Engineering)
  • Feature Paper
  • Article
  • Open Access
5 Citations
4,296 Views
17 Pages

12 February 2024

A temporal knowledge graph represents temporal information between entities in a multi-relational graph. Its reasoning aims to infer and predict potential links among entities. Predicting time-aware entities is a challenging task due to significant d...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
3 Citations
3,595 Views
17 Pages

Combining Classifiers for Deep Learning Mask Face Recognition

  • Wen-Chang Cheng,
  • Hung-Chou Hsiao,
  • Yung-Fa Huang and
  • Li-Hua Li

21 July 2023

This research proposes a single network model architecture for mask face recognition using the FaceNet training method. Three pre-trained convolutional neural networks of different sizes are combined, namely InceptionResNetV2, InceptionV3, and Mobile...

(This article belongs to the Special Issue Blending Artificial Intelligence and Machine Learning with the Internet of Things: Emerging Trends, Issues and Challenges)

of 15