IEEE transactions on neural networks and learning systems最新文献

Accelerated Iterative Learning Control With a Tuning Parameter for Discrete-Time Transfer Function Models 离散时间传递函数模型的带整定参数加速迭代学习控制

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-09 DOI: 10.1109/tnnls.2026.3740973

Ai-Guo Wu, Xiu-Juan Zhao, Rui-Qi Dong, Liang Hu

引用次数: 0

Broad Fuzzy Neural Network-Based Prescribed-Time Control for a Flexible Single-Link Manipulator With Multiple Constraints. 基于广义模糊神经网络的多约束单连杆柔性机械臂规定时间控制。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-06 DOI: 10.1109/TNNLS.2026.3748664

Yan Weng, Zhijia Zhao, Kaili Feng, Qinghua Lu, Lei Liu, Zhijie Liu, C L Philip Chen

{"title":"Broad Fuzzy Neural Network-Based Prescribed-Time Control for a Flexible Single-Link Manipulator With Multiple Constraints.","authors":"Yan Weng, Zhijia Zhao, Kaili Feng, Qinghua Lu, Lei Liu, Zhijie Liu, C L Philip Chen","doi":"10.1109/TNNLS.2026.3748664","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3748664","url":null,"abstract":"Flexible manipulator control can be impacted by vibrations alongside input and output constraints, potentially increasing safety risks or causing serious accidents. This study develops a broad fuzzy neural network (BFNN)-based prescribed-time control (PTC) scheme for a flexible single-link manipulator (FSLM) subject to flexible-link vibration, a compound actuator nonlinearity comprising dead-zone and saturation, and output constraints. The BFNN is employed specifically to estimate and compensate for the actuator-induced mismatch between the commanded and actual control inputs. A two-domain stability analysis establishes semi-global practical finite-time stability (SGPFS) in the transformed time domain and shows that the tracking errors enter an adjustable neighborhood within the user-assigned time in the original time domain. Meanwhile, a barrier Lyapunov function (BLF) ensures that the constrained tracking errors remain within their prescribed bounds. The simulation and hardware experimental results demonstrate prescribed-time tracking, constraint satisfaction, vibration suppression, and practical implementability.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149357371","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

Optimal Adaptive Critic Learning Control of Continuous-Time Nonlinear Systems: A Differential Riccati Equation-Based Method. 连续时间非线性系统的最优自适应评价学习控制：一种基于Riccati微分方程的方法。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-06 DOI: 10.1109/TNNLS.2026.3748127

Bingyi Jia, Jun Zhao, Jing Na, Qingliang Zeng, Zhiwen Wang

{"title":"Optimal Adaptive Critic Learning Control of Continuous-Time Nonlinear Systems: A Differential Riccati Equation-Based Method.","authors":"Bingyi Jia, Jun Zhao, Jing Na, Qingliang Zeng, Zhiwen Wang","doi":"10.1109/TNNLS.2026.3748127","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3748127","url":null,"abstract":"This brief introduces an optimal adaptive critic learning control for continuous-time (CT) nonlinear systems. First, a single-critic neural network (NN) is employed to approximate the solution of the derived Hamilton-Jacobi-Bellman (HJB) equation, with a filtered Bellman residual serving as the mechanism for updating the critic NN weights. To eliminate the necessity of manual tuning of fixed adaptation parameters, the weight error dynamics are reformulated as a CT optimal control problem. Consequently, solving the associated differential Riccati equation (DRE) in real time enables the derivation of an optimal adaptive law that effectively balances the convergence performance and system robustness. Under the condition that regressor signals satisfy a persistent excitation (PE) condition, the critic NN weight errors exponentially converge to a bounded region determined by the approximation residual. The proposed algorithm is validated through experiments on an axial piston pump. The results demonstrate that the proposed learning approach enables fast critic weight convergence while reducing the weight update fluctuations.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149357373","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

Stage-Aware Multimodal Brain Graph Contrastive Learning for Neurodegenerative Disorder Diagnosis. 阶段感知多模态脑图对比学习在神经退行性疾病诊断中的应用。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-06 DOI: 10.1109/TNNLS.2026.3748017

Jingjing Zhou, Chenxuan Meng, Ciyuan Peng, Jing Ren, Feng Xia

{"title":"Stage-Aware Multimodal Brain Graph Contrastive Learning for Neurodegenerative Disorder Diagnosis.","authors":"Jingjing Zhou, Chenxuan Meng, Ciyuan Peng, Jing Ren, Feng Xia","doi":"10.1109/TNNLS.2026.3748017","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3748017","url":null,"abstract":"Neurodegenerative disorders are characterized by their progressive nature, with distinct stages that require precise identification and tracking of progression trajectories for accurate diagnosis. However, existing diagnostic methods often fail to fully capture the unique brain patterns associated with different stages, limiting their ability to effectively target specific stages of the disorders. To address this issue, we propose a stage-aware multimodal brain graph contrastive learning (smBGC) method. In particular, smBGC introduces a stage-aware feature enhancement strategy to capture stage-specific features across all progression stages, enabling the generation of stage-aware multimodal brain graph representations. In addition, smBGC incorporates a stage-adaptive brain graph augmentation approach within a graph contrastive learning (GCL) framework, facilitating multimodal fusion and improving the model's capability to distinguish between different disorder stages. Experiments on two real-world datasets demonstrate the superior performance of smBGC in various neurodegenerative disorder diagnosis tasks compared with state-of-the-art methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149357374","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

Efficient Training of Spiking Neural Networks by Spike-Aware Data Pruning. 基于峰值感知数据修剪的峰值神经网络高效训练。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-06 DOI: 10.1109/TNNLS.2026.3747267

Chenxiang Ma, Xinyi Chen, Yujie Wu, Kay Chen Tan, Jibin Wu

{"title":"Efficient Training of Spiking Neural Networks by Spike-Aware Data Pruning.","authors":"Chenxiang Ma, Xinyi Chen, Yujie Wu, Kay Chen Tan, Jibin Wu","doi":"10.1109/TNNLS.2026.3747267","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3747267","url":null,"abstract":"Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable training overhead, posing challenges for researchers with limited computational resources and hindering the sustained development of SNNs. Data pruning is a promising strategy for accelerating training by retaining the most informative examples and discarding redundant ones, but it remains largely unexplored in SNNs. Directly applying ANN-based data pruning methods to SNNs fails to capture the intrinsic importance of examples and suffers from high gradient variance. To address these challenges, we propose a novel spike-aware data pruning (SADP) method. SADP reduces gradient variance by determining each example's selection probability to be proportional to its gradient norm, while avoiding the high cost of direct gradient computation through an efficient upper bound, termed spike-aware importance score. This score accounts for the influence of all-or-nothing spikes on the gradient norm and can be computed with negligible overhead. Extensive experiments across diverse datasets and architectures demonstrate that SADP consistently outperforms data pruning baselines and achieves training speedups close to the theoretical maxima at different pruning ratios. Notably, SADP reduces training time by 35% on ImageNet while maintaining accuracy comparable to that of full-data training. This work, therefore, establishes a data-centric paradigm for efficient SNN training and paves the way for scaling SNNs to larger models and datasets. Code is available at https://github.com/ChenxiangMA/SADP.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149357372","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

Distributed Strategies for Multiagent Constrained Min–Max Optimization 多智能体约束最小最大优化的分布式策略

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-05 DOI: 10.1109/tnnls.2026.3744548

Yao Zou, Ziyang Meng, Wei He, Keum-Shik Hong

引用次数: 0

Dynamical Versus Bayesian Phase Transitions in a Toy Model of Superposition 动态与贝叶斯的相变在一个玩具模型的叠加

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-05 DOI: 10.1109/tnnls.2026.3739685

Zhongtian Chen, Edmund Lau, Jake Mendel, Susan Wei, Daniel Murfet

引用次数: 0

Tilted Neural Additive Models. 倾斜神经加性模型。

IF 9.7 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-05 DOI: 10.1109/TNNLS.2026.3745087

Yingjie Wang, Liqun Deng, Yuyang Zhang, Baodi Liu, Jingcheng Wang, Weifeng Liu

{"title":"Tilted Neural Additive Models.","authors":"Yingjie Wang, Liqun Deng, Yuyang Zhang, Baodi Liu, Jingcheng Wang, Weifeng Liu","doi":"10.1109/TNNLS.2026.3745087","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3745087","url":null,"abstract":"Neural additive models (NAMs) have recently attracted increasing attention due to their strong predictive performance and desirable interpretability. However, most existing approaches rely on empirical risk minimization (ERM), which often underperform in challenging scenarios where average performance is not a suitable criterion for the problems of interest, such as complex noise perturbation. In this article, we address these challenges by learning sparse NAMs under the tilted ERM (TERM) framework. The proposed approach retains feature-level interpretability while exhibiting robustness to a broad class of complex noise perturbations. On the theoretical side, we develop oracle-type function approximation analyses for the proposed method under both independent identically distributed (i.i.d.) and stationary $beta $ -mixing settings, yielding explicit error bounds that characterize how noise structure, model complexity, and the tilting mechanism of TERM jointly affect robustness performance. Empirical evaluations on synthetic and real-world coronal mass ejections (CMEs) datasets demonstrate the effectiveness and competitiveness of our approach.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149341974","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

Approximated Prompt Tuning for Vision–Language Pretrained Models 视觉语言预训练模型的近似提示调谐

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-05 DOI: 10.1109/tnnls.2026.3741667

Qiong Wu, Yiyi Zhou, Shubin Huang, Pingyang Dai, Rongrong Ji

引用次数: 0

RSTLNet: A Robust Spatiotemporal Learning Framework for Network Traffic Matrix Imputation RSTLNet：一个鲁棒的网络流量矩阵输入时空学习框架

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2026-11-05 DOI: 10.1109/tnnls.2026.3745146

Kaiyuan Zheng, Yuxuan Liang, Huile Wang, Gansen Zhao, Xiaomao Fan, Weiping Zheng

引用次数: 0