IEEE transactions on neural networks and learning systems最新文献_第8页

Theoretical Advances on Stochastic Configuration Networks. 随机构型网络的理论进展。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-16 DOI: 10.1109/tnnls.2025.3608555

Xiufeng Yan,Dianhui Wang,Ivan Y Tyukin

{"title":"Theoretical Advances on Stochastic Configuration Networks.","authors":"Xiufeng Yan,Dianhui Wang,Ivan Y Tyukin","doi":"10.1109/tnnls.2025.3608555","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3608555","url":null,"abstract":"This article advances the theoretical foundations of stochastic configuration networks (SCNs) by rigorously analyzing their convergence properties, approximation guarantees, and the limitations of nonadaptive randomized methods. We introduce a principled objective function that aligns incremental training with orthogonal projection, ensuring maximal residual reduction at each iteration without recomputing output weights. Under this formulation, we derive a novel necessary and sufficient condition for strong convergence in Hilbert spaces and establish sufficient conditions for uniform geometric convergence, offering the first theoretical justification of the SCN residual constraint. To assess the feasibility of unguided random initialization, we present a probabilistic analysis showing that even small support shifts markedly reduce the likelihood of sampling effective nodes in high-dimensional settings, thereby highlighting the necessity of adaptive refinement in the sampling distribution. Motivated by these insights, we propose greedy SCNs (GSCNs) and two optimized variants-Newton-Raphson GSCN (NR-GSCN) and particle swarm optimization GSCN (PSO-GSCN)-that incorporate Newton-Raphson refinement and particle swarm-based exploration to improve node selection. Empirical results on synthetic and real-world datasets demonstrate that the proposed methods achieve faster convergence, better approximation accuracy, and more compact architectures compared to existing SCN training schemes. Collectively, this work establishes a rigorous theoretical and algorithmic framework for SCNs, laying out a principled foundation for subsequent developments in the field of randomized neural network (NN) training.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"124 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145072126","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

FEU-Diff: A Diffusion Model With Fuzzy Evidence-Driven Dynamic Uncertainty Fusion for Medical Image Segmentation. FEU-Diff：一种基于模糊证据驱动动态不确定性融合的医学图像分割扩散模型。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-16 DOI: 10.1109/tnnls.2025.3609085

Sheng Geng,Shu Jiang,Tao Hou,Hongcheng Yao,Jiashuang Huang,Weiping Ding

{"title":"FEU-Diff: A Diffusion Model With Fuzzy Evidence-Driven Dynamic Uncertainty Fusion for Medical Image Segmentation.","authors":"Sheng Geng,Shu Jiang,Tao Hou,Hongcheng Yao,Jiashuang Huang,Weiping Ding","doi":"10.1109/tnnls.2025.3609085","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3609085","url":null,"abstract":"Diffusion models, as a class of generative frameworks based on step-wise denoising, have recently attracted significant attention in the field of medical image segmentation. However, existing diffusion-based methods typically rely on static fusion strategies to integrate conditional priors with denoised features, making them difficult to adaptively balance their respective contributions at different denoising stages. Moreover, these methods often lack explicit modeling of pixel-level uncertainty in ambiguous regions, which may lead to the loss of structural details during the iterative denoising process, ultimately compromising the accuracy (Acc) and completeness of the final segmentation results. To this end, we propose FEU-Diff, a diffusion-based segmentation framework that integrates fuzzy evidence modeling and uncertainty fusion (UF) mechanisms. Specifically, a fuzzy semantic enhancement (FSE) module is designed to model pixel-level uncertainty through Gaussian membership functions and fuzzy logic rules, enhancing the model's ability to identify and represent ambiguous boundaries. An evidence dynamic fusion (EDF) module estimates feature confidence via a Dirichlet-based distribution and adaptively guides the fusion of conditional information and denoised features across different denoising stages. Furthermore, the UF module quantifies discrepancies among multisource predictions to compensate for structural detail loss during the iterative denoising process. Extensive experiments on four public datasets show that FEU-Diff consistently outperforms state-of-the-art (SOTA) methods, achieving an average gain of 1.42% in the Dice similarity coefficient (DSC), 1.47% in intersection over union (IoU), and a 2.26 mm reduction in the 95th percentile Hausdorff distance (HD95). In addition, our method generates uncertainty maps that enhance clinical interpretability.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"16 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145072123","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

Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer-Based Dim Object Detection. 基于脑眼机的模糊目标检测自适应模态平衡在线知识提炼。

IF 8.9 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-15 DOI: 10.1109/TNNLS.2025.3605710

Zixing Li, Chao Yan, Zhen Lan, Xiaojia Xiang, Han Zhou, Jun Lai, Dengqing Tang

{"title":"Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer-Based Dim Object Detection.","authors":"Zixing Li, Chao Yan, Zhen Lan, Xiaojia Xiang, Han Zhou, Jun Lai, Dengqing Tang","doi":"10.1109/TNNLS.2025.3605710","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3605710","url":null,"abstract":"<p><p>Advanced cognition can be measured from the human brain using brain-computer interfaces (BCIs). Integrating these interfaces with computer vision techniques, which possess efficient feature extraction capabilities, can achieve more robust and accurate detection of dim targets in aerial images. However, existing target detection methods primarily concentrate on homogeneous data, lacking efficient and versatile processing capabilities for heterogeneous multimodal data. In this article, we first build a brain-eye-computer-based object detection system for aerial images under few-shot conditions. This system detects suspicious targets using region proposal networks (RPNs), evokes the event-related potential (ERP) signal in electroencephalogram (EEG) through the eye-tracking-based slow serial visual presentation (ESSVP) paradigm, and constructs the EEG-image data pairs with eye movement data. Then, an adaptive modality balanced online knowledge distillation (AMBOKD) method is proposed to recognize dim objects with the EEG-image data. AMBOKD fuses EEG and image features using a multihead attention module, establishing a new modality with comprehensive features. To enhance the performance and robust capability of the fusion modality, simultaneous training and mutual learning between modalities are enabled by end-to-end online KD (OKD). During the learning process, an adaptive modality balancing module is proposed to ensure multimodal equilibrium by dynamically adjusting the weights of the importance and the training gradients across various modalities. The effectiveness and superiority of our method are demonstrated by comparing it with existing state-of-the-art methods. Additionally, experiments conducted on public datasets and real-world scenarios demonstrate the reliability and practicality of the proposed system and the designed method. The dataset and the source code can be found at: https://github.com/lizixing23/AMBOKD.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145069479","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

AMAP: Automatic Multihead Attention Pruning by Similarity-Based Pruning Indicator. 基于相似性修剪指示器的多头注意力自动修剪。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-15 DOI: 10.1109/tnnls.2025.3606750

Eunho Lee,Youngbae Hwang

{"title":"AMAP: Automatic Multihead Attention Pruning by Similarity-Based Pruning Indicator.","authors":"Eunho Lee,Youngbae Hwang","doi":"10.1109/tnnls.2025.3606750","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3606750","url":null,"abstract":"Despite the strong performance of transformers, quadratic computation complexity of self-attention presents challenges in applying them to vision tasks. Linear attention reduces this complexity from quadratic to linear, offering a strong computation-performance tradeoff. To further optimize this, automatic pruning is an effective method to find a structure that maximizes performance within a target resource through training without any heuristic approaches. However, directly applying it to multihead attention is not straightforward due to channel mismatch. In this article, we propose an automatic pruning method to deal with this problem. Different from existing methods that rely solely on training without any prior knowledge, we integrate channel similarity-based weights into the pruning indicator to preserve the more informative channels within each head. Then, we adjust the pruning indicator to enforce that channels are removed evenly across all heads, thereby avoiding any channel mismatch. We incorporate a reweight module to mitigate information loss due to channel removal and introduce an effective pruning indicator initialization for linear attention, based on the attention differences between the original structure and each channel. By applying our pruning method to the FLattenTransformer on ImageNet-1K, which incorporates original and linear attention mechanisms, we achieve a 30% reduction of FLOPs in a near lossless manner. It also has 1.96% of accuracy gain over the DeiT-B model while reducing FLOPs by 37%, and 1.05% accuracy increase over the Swin-B model with a 10% reduction in FLOPs as well. The proposed method outperforms previous state-of-the-art efficient models and the recent pruning methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"72 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145068376","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

Channelwise Regional Integrate and Multiple Firing Neuron: Improving the Spatiotemporal Learning of Spiking Neural Networks 通道区域整合和多放电神经元：改进脉冲神经网络的时空学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-11 DOI: 10.1109/tnnls.2025.3606849

Mincheng Cai, Quan Liu, Kun Chen, Li Ma

引用次数: 0

Conv4Rec: A 1-by-1 Convolutional Autoencoder for User Profiling Through Joint Analysis of Implicit and Explicit Feedback 基于隐式和显式反馈联合分析的1 × 1卷积自编码器

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-11 DOI: 10.1109/tnnls.2025.3597051

Antoine Ledent, Petr Kasalický, Rodrigo Alves, Hady W. Lauw

引用次数: 0

When to Align: Dynamic Behavior Consistency for Multiagent Systems via Intrinsic Rewards. 何时对齐：通过内在奖励的多智能体系统的动态行为一致性。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-10 DOI: 10.1109/tnnls.2025.3598301

Kunyang Lin,Yufeng Wang,Peihao Chen,Runhao Zeng,Yinjie Lei,Siyuan Zhou,Qing Du,Mingkui Tan,Chuang Gan

{"title":"When to Align: Dynamic Behavior Consistency for Multiagent Systems via Intrinsic Rewards.","authors":"Kunyang Lin,Yufeng Wang,Peihao Chen,Runhao Zeng,Yinjie Lei,Siyuan Zhou,Qing Du,Mingkui Tan,Chuang Gan","doi":"10.1109/tnnls.2025.3598301","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3598301","url":null,"abstract":"In multiagent systems, learning optimal behavior policies for individual agents remains a challenging yet crucial task. While recent research has made strides in this area, the issue of when agents should maintain consistent behaviors with one another is still not adequately addressed. This article proposes a novel approach to enable agents to autonomously decide whether their behaviors should align with those of their peers by leveraging intrinsic rewards to optimize their policies. We define behavior consistency as the divergence between the actions taken by two agents given the same observations. To encourage agents to be aware of each other's behaviors, we propose dynamic consistency-based intrinsic reward (DCIR), which guides agents in determining when to synchronize their behaviors. In addition, we introduce a dynamic scaling network (DSN) that provides learnable scaling factors at each time step, enabling agents to dynamically decide the extent of rewarding consistent behavior. Our method is evaluated on environments including Multiagent Particle, Google Research Football, and StarCraft II Micromanagement. Experimental results demonstrate its effectiveness in learning optimal policies.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"12 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031964","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 Modeling With Frozen Vision-Language Foundation Models for Parameter-Efficient Text-Video Retrieval. 基于冻结视觉语言基础模型的时间建模用于参数高效文本视频检索。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-09 DOI: 10.1109/tnnls.2025.3605657

Leqi Shen,Tianxiang Hao,Tao He,Yifeng Zhang,Pengzhang Liu,Sicheng Zhao,Jungong Han,Guiguang Ding

{"title":"Temporal Modeling With Frozen Vision-Language Foundation Models for Parameter-Efficient Text-Video Retrieval.","authors":"Leqi Shen,Tianxiang Hao,Tao He,Yifeng Zhang,Pengzhang Liu,Sicheng Zhao,Jungong Han,Guiguang Ding","doi":"10.1109/tnnls.2025.3605657","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3605657","url":null,"abstract":"Temporal modeling plays an important role in the effective adaption of the powerful pretrained text-image foundation model into text-video retrieval. However, existing methods often rely on additional heavy trainable modules, such as transformer or BiLSTM, which are inefficient. In contrast, we avoid introducing such heavy components by leveraging frozen foundation models. To this end, we propose temporal modeling with frozen vision-language foundation models (TFVL) to model the temporal dynamics with fixed encoders. Specifically, text encoder temporal modeling (TextTemp) and image encoder temporal modeling (ImageTemp) apply frozen text and image encoders within the video head and video backbone, respectively. TextTemp uses a frozen text encoder to interpret frame representations as \"visual words\" within a temporal \"sentence,\" capturing temporal dependencies. On the other hand, ImageTemp uses a frozen image encoder to treat all frame tokens as a unified visual entity, learning spatiotemporal information. The total trainable parameters of our method, comprising a lightweight projection and several prompt tokens, are significantly fewer than those in other existing methods. We evaluate the effectiveness of our method on MSR-VTT, DiDeMo, ActivityNet, and LSMDC. Compared with full fine-tuning on MSR-VTT, our TFVL achieves an average 3.25% gain in R@1 with merely 0.35% of the parameters. Extensive experiments demonstrate that the proposed TFVL outperforms state-of-the-art methods with significantly fewer parameters.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"15 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145025296","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

Robust Missing Value Imputation With Proximal Optimal Transport for Low-Quality IIoT Data. 基于最优传输的低质量IIoT数据鲁棒缺失值输入。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-09 DOI: 10.1109/tnnls.2025.3601130

Hao Wang,Zhichao Chen,Yuan Shen,Hui Zheng,Degui Yang,Dangjun Zhao,Buge Liang

{"title":"Robust Missing Value Imputation With Proximal Optimal Transport for Low-Quality IIoT Data.","authors":"Hao Wang,Zhichao Chen,Yuan Shen,Hui Zheng,Degui Yang,Dangjun Zhao,Buge Liang","doi":"10.1109/tnnls.2025.3601130","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3601130","url":null,"abstract":"Accurate imputation of missing data is crucial in the Industrial Internet-of-Things (IIoT), where operations are often compromised by noisy samples from harsh environments. Traditional imputation methods struggle with such noise due to their black-box nature or lack of adaptability. To address this issue, we recast data imputation as a distribution alignment challenge, utilizing the flexibility of optimal transport (OT) to handle noisy samples. Specifically, we first introduce the Proximal Optimal Transport (POT) problem, where the transportation cost is obtained by the network simplex approach with a selective matching mechanism, which renders it capable of matching distributions with noisy samples. Subsequently, we propose the POT-I framework, where the objective is to minimize the transport cost of POT. The produced gradient is used to refine the imputation value, which achieves missing data imputation (MDI) while getting robustness to noisy samples. Experiments on real-world IIoT datasets demonstrate the superiority of POT-I over state-of-the-art imputation methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"2 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145025292","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

Bicriteria Policy Optimization for High-Accuracy Reinforcement Learning. 高精度强化学习的双准则策略优化。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-09-09 DOI: 10.1109/tnnls.2025.3605362

Guojian Zhan,Xiangteng Zhang,Feihong Zhang,Letian Tao,Shengbo Eben Li

{"title":"Bicriteria Policy Optimization for High-Accuracy Reinforcement Learning.","authors":"Guojian Zhan,Xiangteng Zhang,Feihong Zhang,Letian Tao,Shengbo Eben Li","doi":"10.1109/tnnls.2025.3605362","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3605362","url":null,"abstract":"In essence, reinforcement learning (RL) solves optimal control problem (OCP) by employing a neural network (NN) to fit the optimal policy from state to action. The accuracy of policy approximation is often very low in complex control tasks, leading to unsatisfactory control performance compared with online optimal controllers. A primary reason is that the landscape of value function is always not only rugged in most areas but also flat on the bottom, which damages the convergence to the minimum point. To address this issue, we develop a bicriteria policy optimization (BPO) algorithm, which leverages a few optimal demonstration trajectories to guide the policy search at the gradient level. Different from conventional problem definition, BPO seeks to solve a bicriteria OCP, which has two homomorphic objectives: one is from the standard reward signals and the other is to align the demonstration trajectories. We introduce two co-state variables, one for each objectives, and formulate two Hamiltonians for this bicriteria OCP. The resulting new optimality condition preserves the minimum values of both Hamiltonians. Furthermore, we find that gradient conflict is a key obstacle to simultaneously descending both Hamiltonians, and its impact is negatively proportional to the inner product between the ideal and actual gradients. A minimax optimization problem is built at each RL iteration to minimize conflicts between two homomorphic objectives, whose solution for policy updating is referred to as harmonic gradient. By converting its inner optimization loop into a linear programming with convex trust region constraint, we simplify this problem into a single-loop maximization problem with much increased computational efficiency. Experiment tests on both linear and nonlinear control tasks validate the effectiveness of our BPO algorithm on the accuracy improvement of policy network.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"43 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145025795","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