IEEE transactions on neural networks and learning systems最新文献_第3页

Time-Series Contrastive Learning Against False Negatives and Class Imbalance 时间序列对比学习对抗假阴性与阶级不平衡

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-23 DOI: 10.1109/tnnls.2025.3568387

Xiyuan Jin, Jing Wang, Xiaoyu Ou, Lei Liu, Youfang Lin

引用次数: 0

RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation RSF-Conv：旋转尺度等变傅里叶参数化卷积视网膜血管分割

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-23 DOI: 10.1109/tnnls.2025.3560082

Zihong Sun, Hong Wang, Qi Xie, Yefeng Zheng, Deyu Meng

引用次数: 0

Probabilistic Safety Regions via Finite Families of Adjustable Classifiers 基于可调分类器有限族的概率安全区域

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-23 DOI: 10.1109/tnnls.2025.3568174

Alberto Carlevaro, Teodoro Alamo, Fabrizio Dabbene, Maurizio Mongelli

引用次数: 0

A Novel Dynamic Neural Network for Heterogeneity-Aware Structural Brain Network Exploration and Alzheimer's Disease Diagnosis. 一种新的动态神经网络用于异质性感知结构脑网络探索和阿尔茨海默病诊断。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-22 DOI: 10.1109/tnnls.2025.3569650

Wenju Cui,Yilin Leng,Yunsong Peng,Chen Bai,Lei Li,Xi Jiang,Gang Yuan,Jian Zheng

{"title":"A Novel Dynamic Neural Network for Heterogeneity-Aware Structural Brain Network Exploration and Alzheimer's Disease Diagnosis.","authors":"Wenju Cui,Yilin Leng,Yunsong Peng,Chen Bai,Lei Li,Xi Jiang,Gang Yuan,Jian Zheng","doi":"10.1109/tnnls.2025.3569650","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3569650","url":null,"abstract":"Heterogeneity is a fundamental characteristic of brain diseases, distinguished by variability not only in brain atrophy but also in the complexity of neural connectivity and brain networks. However, existing data-driven methods fail to provide a comprehensive analysis of brain heterogeneity. Recently, dynamic neural networks (DNNs) have shown significant advantages in capturing sample-wise heterogeneity. Therefore, in this article, we first propose a novel dynamic heterogeneity-aware network (DHANet) to identify critical heterogeneous brain regions, explore heterogeneous connectivity between them, and construct a heterogeneous-aware structural brain network (HGA-SBN) using structural magnetic resonance imaging (sMRI). Specifically, we develop a 3-D dynamic convmixer to extract abundant heterogeneous features from sMRI first. Subsequently, the critical brain atrophy regions are identified by dynamic prototype learning with embedding the hierarchical brain semantic structure. Finally, we employ a joint dynamic edge-correlation (JDE) modeling approach to construct the heterogeneous connectivity between these regions and analyze the HGA-SBN. To evaluate the effectiveness of the DHANet, we conduct elaborate experiments on three public datasets and the method achieves state-of-the-art (SOTA) performance on two classification tasks.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"2 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144122161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Revising Representation and Target Deviations for Accurate Human Pose Estimation. 修正人体姿态估计的表示和目标偏差。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-22 DOI: 10.1109/tnnls.2025.3569464

Zian Zhang,Yongqiang Zhang,Yancheng Bai,Man Zhang,Rui Tian,Yin Zhang,Mingli Ding,Wangmeng Zuo

{"title":"Revising Representation and Target Deviations for Accurate Human Pose Estimation.","authors":"Zian Zhang,Yongqiang Zhang,Yancheng Bai,Man Zhang,Rui Tian,Yin Zhang,Mingli Ding,Wangmeng Zuo","doi":"10.1109/tnnls.2025.3569464","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3569464","url":null,"abstract":"Owing to the normalized instance scales and robust supervision, heatmap-based human pose estimation (HPE) methods with top-down paradigm have achieved a dominant performance. However, there are two inherent deviations in the basic framework, i.e., representation and target deviations, resulting in performance bottlenecks. The representation deviation is caused by transforming various scales of instances into a unified input size, which results in performance degradation because data with different scale-related characteristics can hardly be handled via unified parameters. The target deviation is caused by exploiting a prior distribution (e.g., Gauss) to model the prediction error, which hinders sufficient network training. In this article, we propose a novel framework called DRPose to revise the abovementioned deviations. Specifically, to address the representation deviation, a scale-aware domain bridging (SDB) block is proposed to transfer feature maps from multiple scale-dependent domains into a unified intermediate domain with dynamic parameters. To address the target deviation, a differentiable coordinate decoder (DCD) is presented to adaptively adjust target distribution of heatmaps in an end-to-end manner. Extensive experiments show that the proposed method significantly improves the performance of most existing models with negligible additional cost. Beyond this, our method achieves 77.1% AP on the COCO test-dev set, outperforming prior works with similar model complexity.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"4 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144122160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Training Dataset Curation by L 1-Norm Principal-Component Analysis for Support Vector Machines. 基于L -范数主成分分析的支持向量机训练数据集管理。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-22 DOI: 10.1109/tnnls.2025.3568694

Shruti Shukla,Dimitris A Pados,George Sklivanitis,Elizabeth Serena Bentley,Michael J Medley

{"title":"Training Dataset Curation by L 1-Norm Principal-Component Analysis for Support Vector Machines.","authors":"Shruti Shukla,Dimitris A Pados,George Sklivanitis,Elizabeth Serena Bentley,Michael J Medley","doi":"10.1109/tnnls.2025.3568694","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3568694","url":null,"abstract":"Support vector machines (SVMs) have been the learning model of choice in numerous classification applications. While SVMs are widely successful in real-world deployments, they remain susceptible to mislabeled examples in training datasets where the presence of few faults can severely affect decision boundaries, thereby affecting the model's performance on unseen data. In this brief, we develop and describe in implementation detail a novel method based on $L_{1}$ -norm principal-component data analysis and geometry that aims to filter out atypical data instances on a class-by-class basis before the training phase of SVMs and thus provide the classifier with robust support-vector candidates for making classification boundaries. The proposed dataset curation method is entirely data-driven (touch-free), unsupervised, and computationally efficient. Extensive experimental studies on real datasets included in this brief illustrate the $L_{1}$ -norm curation method and demonstrate its efficacy in protecting SVM models from data faults during learning.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"60 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144122162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Factorization-Based Broad Learning System With Time-Dependent Structure 具有时变结构的分解广义学习系统

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-21 DOI: 10.1109/tnnls.2025.3567757

Chen Li, Zeyi Liu, Xiao He, Pengyu Han

引用次数: 0

An Efficient and Robust Feature Selection Approach Based on Zentropy Measure and Neighborhood-Aware Model 基于z熵测度和邻域感知模型的高效鲁棒特征选择方法

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-21 DOI: 10.1109/tnnls.2025.3565320

Kehua Yuan, Duoqian Miao, Hongyun Zhang, Witold Pedrycz

引用次数: 0

Enhancing Multiparty Dialog Discourse Parsing With Dynamic Task-Adaptive Graph Transformer and Difficulty-Aware Task Scheduling 利用动态任务自适应图转换器和困难感知任务调度增强多方对话语篇解析

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-21 DOI: 10.1109/tnnls.2025.3568211

Yaxin Fan, Peifeng Li, Fang Kong, Qiaoming Zhu

引用次数: 0

Complex Dual-Tree Pyramid Scattering Transformer 复杂双树金字塔散射变压器

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-21 DOI: 10.1109/tnnls.2025.3565582

Xiaotong Li, Licheng Jiao, Lingling Li, Fang Liu, Hao Zhu, Xin Zhang, Xu Liu, Shuyuan Yang

引用次数: 0