IEEE transactions on neural networks and learning systems最新文献

Self-Adaptive Background-Attentive Network With Anomaly Suppression for Hyperspectral Anomaly Detection.

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-19 DOI: 10.1109/TNNLS.2026.3741742

Xu Liu, Hao Yuan, Bohui Tang, Qingquan Li, Chao Yang, Tiezhu Shi, Daming Zhu

{"title":"Self-Adaptive Background-Attentive Network With Anomaly Suppression for Hyperspectral Anomaly Detection.","authors":"Xu Liu, Hao Yuan, Bohui Tang, Qingquan Li, Chao Yang, Tiezhu Shi, Daming Zhu","doi":"10.1109/TNNLS.2026.3741742","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3741742","url":null,"abstract":"In recent years, deep learning has emerged as one of the prominent technologies in hyperspectral anomaly detection (HAD) due to its powerful feature extraction capability. Deep learning-based methods aim to reconstruct the background image and use the reconstruction error as a criterion for anomaly detection. However, existing methods rarely exploit the spatial and spectral differences between background and anomalies to suppress anomaly reconstruction. To overcome this limitation, we propose a self-adaptive background-attentive network with anomaly suppression (BASNet). Specifically, a pyramid similarity downsampling module (PSDM) is employed to reduce the proportion of anomalies in the input image and improve multiscale background representation. To enhance the network's attention to background information, a multiscale attention module (MAM) is designed, and an inverse attention strategy is adopted to guide the network to focus on background regions. In addition, a depthwise separable blind-block convolution module (DBCM) is constructed for pixel reconstruction. This module applies weighted multiscale blind-block convolutions according to the anomaly score of each pixel, allowing the network to effectively handle anomalies at different scales. Due to the stochastic nature of deep learning, the optimal stopping epoch for network training is not fixed. Therefore, reconstructed image difference (RID) is developed to dynamically determine the stopping epoch. Extensive experiments on eight datasets demonstrate that the proposed BASNet achieves satisfactory detection performance.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149223903","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

Interrupted Sampling Repeater Jamming Suppression for Wideband Radar With MCA-ADMM-Net. 基于MCA-ADMM-Net的宽带雷达干扰抑制

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-13 DOI: 10.1109/TNNLS.2026.3736439

Shaopeng Wei, Haoyu Han, Haonan Zhang, Song Wei, Yejian Zhou, Lei Zhang

{"title":"Interrupted Sampling Repeater Jamming Suppression for Wideband Radar With MCA-ADMM-Net.","authors":"Shaopeng Wei, Haoyu Han, Haonan Zhang, Song Wei, Yejian Zhou, Lei Zhang","doi":"10.1109/TNNLS.2026.3736439","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3736439","url":null,"abstract":"Wideband radar is widely used for imaging and recognition in both military and civilian applications, such as remote sensing and guided strikes. With the advancement of electronic support systems, wideband radar is increasingly susceptible to complex electromagnetic environments. Among these jamming types, interrupted sampling repeater jamming (ISRJ) exhibits characteristics such as rapid interrupted sampling, high power, strong correlation, and complex modulation, which can generate numerous false targets and lead to misjudgments in radar systems. To address this issue, we propose an ISRJ suppression method based on joint morphological component analysis (MCA) and deep unfolding networks. We analyze the structural differences between target echoes and ISRJ signals, which can be sparsely represented under two approximately orthogonal dictionaries. The MCA optimization model is then introduced to simultaneously estimate the target echoes and ISRJ. To circumvent the challenges of hyperparameter determination, we derive an unfolding network based on the alternating direction method of multipliers (ADMM), enabling adaptive hyperparameter selection and optimization solutions with limited iterations in a data-driven manner. This method offers the advantages of adaptive hyperparameter tuning and robustness to varying jamming-to-signal-and-noise ratios (JSNRs). In addition, it achieves simultaneous jamming suppression and complete target echo preservation within the MCA framework. Finally, simulation and real-world experiments validate the effectiveness of this approach.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181523","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

Feature Selection for Incomplete Hierarchical Data by Positive Weight Recovery and Implicit Hierarchical Information. 基于正权恢复和隐式层次信息的不完全层次数据特征选择。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-08 DOI: 10.1109/TNNLS.2026.3736598

Jianhua Dai, Shiyu Wei

{"title":"Feature Selection for Incomplete Hierarchical Data by Positive Weight Recovery and Implicit Hierarchical Information.","authors":"Jianhua Dai, Shiyu Wei","doi":"10.1109/TNNLS.2026.3736598","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3736598","url":null,"abstract":"In real-world applications, hierarchical data with complex category structures pose significant challenges due to high dimensionality and potential incompleteness. Existing studies on hierarchical feature selection assume data are complete, without considering incomplete hierarchical data. However, in practice, obtaining a complete and uncorrupted feature space can be challenging due to physical, technical, and cost constraints in data collection. To address this issue, we propose a hierarchical feature selection method for incomplete hierarchical data. First, weight amendment matrices are introduced to shift the primary missing-data compensation from the feature space to the projection-weight space under hierarchical structural guidance. Second, we establish a hierarchical interaction framework that explicitly captures the implicit relationship between the weight amendment matrix and the hierarchical weight matrix via constrained optimization. Third, we design a sparse hierarchical regularization term that adaptively adjusts feature weights based on hierarchy levels. Extensive experiments on benchmark datasets demonstrate the proposed approach's superior performance over state-of-the-art methods, validating its enhanced effectiveness and progress in addressing the target problem domain.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136359","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

Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects. 脉冲神经网络用于时间处理：现状与未来展望。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-08 DOI: 10.1109/TNNLS.2026.3736737

Chenxiang Ma, Xinyi Chen, Yanchen Li, Qu Yang, Yujie Wu, Guoqi Li, Gang Pan, Huajin Tang, Kay Chen Tan, Jibin Wu

{"title":"Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects.","authors":"Chenxiang Ma, Xinyi Chen, Yanchen Li, Qu Yang, Yujie Wu, Guoqi Li, Gang Pan, Huajin Tang, Kay Chen Tan, Jibin Wu","doi":"10.1109/TNNLS.2026.3736737","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3736737","url":null,"abstract":"Temporal processing is fundamental for biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking neural networks (SNNs) are well-suited for efficient temporal processing owing to their rich neuronal dynamics and event-driven computation. Given the recent surge in the development of SNNs, there is an urgent need for a comprehensive evaluation of their temporal processing capabilities. In this article, we first conduct an in-depth assessment of commonly used neuromorphic benchmarks, revealing critical limitations in their ability to evaluate the temporal processing capabilities of SNNs. To bridge this gap, we further introduce a benchmark suite consisting of four tasks characterized by rich temporal dependencies across multiple timescales. Utilizing this benchmark suite, we comprehensively evaluate recently introduced SNN approaches. Our results demonstrate substantial progress in neuron models, normalization methods, and neural architectures, while also uncovering challenges for online learning and long-range temporal dependencies compared to nonspiking sequence models. These findings establish a comprehensive understanding of the current state of SNNs in temporal processing and lay the foundation for the advancement of neuromorphic algorithms toward efficient operation in dynamic environments.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136365","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

Temporal-Directional Tree-Walk Graph Neural Network for Illicit Transaction Detection 用于非法交易检测的时间定向树行图神经网络

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-06 DOI: 10.1109/tnnls.2026.3732968

Wenyu Zhang, Yunzhu Chen, Neng Ye, Chen Jason Zhang, Xiangming Li

引用次数: 0

Bayesian Frequency-Adaptive and Cross-Scale Neural Signal Modeling for Energy Systems 能源系统贝叶斯频率自适应和跨尺度神经信号建模

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-06 DOI: 10.1109/tnnls.2026.3735964

Mehrnaz Ahmadi, Mehdi Khashei

引用次数: 0

Minorization–Maximization for Ratio Sum Linear Discriminant Analysis 比率和线性判别分析的最小化-最大化

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-05 DOI: 10.1109/tnnls.2026.3734802

Jianhua Zhao, Guanliang Huang, Xuan Ma

引用次数: 0

Understanding and Optimizing Counterfactual Generation in LLMs via Contribution Attribution and Target Intervention 基于贡献归因和目标干预的法学硕士反事实生成理解与优化

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-05 DOI: 10.1109/tnnls.2026.3733646

Hongbo Kou, Chenyu Yao, Ye Song, Deshen Li, Tingqian Shi, Zihan Wang, Chunhua Yang, Weihua Gui

引用次数: 0

CardioODE-Track: Learning Bidirectional Cardiac Motion With Neural ODEs CardioODE-Track：用神经ode学习双向心脏运动

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-02 DOI: 10.1109/tnnls.2026.3735829

Dongsheng Ruan, Chenyi Zhu, Luyan Zheng, Zhifan Gao, Chengjin Yu, Mingfeng Jiang, Huafeng Liu

引用次数: 0

Generative Enhancement of Noninvasive Datasets for Motor Brain–Computer Interface by Synthesizing Task-Relevant Neural Signals 基于任务相关神经信号合成的运动脑机接口无创数据集生成增强

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-10-01 DOI: 10.1109/tnnls.2026.3736056

HongJune Kim, June Sic Kim

引用次数: 0