IEEE transactions on neural networks and learning systems最新文献_第10页

Federated Scientific Machine Learning for Approximating Functions and Solving Differential Equations With Data Heterogeneity 基于数据异质性的近似函数和求解微分方程的联邦科学机器学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-27 DOI: 10.1109/tnnls.2025.3580409

Handi Zhang, Langchen Liu, Kangyu Weng, Lu Lu

引用次数: 0

Spatial–Spectral Heterogeneity-Aware Network for Hyperspectral and LiDAR Joint Classification 高光谱与激光雷达联合分类的空间光谱异质性感知网络

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-27 DOI: 10.1109/tnnls.2025.3577231

Shenfu Zhang, Qiang Liu, Zhenhua Zhang, Rui Zhao, Liang Chen, Feng Shao, Xiangchao Meng

引用次数: 0

MonOri: Orientation-Guided PnP for Monocular 3-D Object Detection 单目三维目标检测的方向导向PnP

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-27 DOI: 10.1109/tnnls.2025.3577618

Hongdou Yao, Pengfei Han, Jun Chen, Zheng Wang, Yansheng Qiu, Xiao Wang, Yimin wang, Xiaoyu Chai, Chenglong Cao, Wei Jin

引用次数: 0

Lifelong Active Inference of Gait Control 步态控制的终身主动推理

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-26 DOI: 10.1109/tnnls.2025.3579814

Rudolf Szadkowski, Jan Faigl

引用次数: 0

Neighboring State-Aware Policy for Deep Reinforcement Learning 深度强化学习的邻接状态感知策略

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-26 DOI: 10.1109/tnnls.2025.3581217

Meng Xu, Xinhong Chen, Guanyi Zhao, Zihao Wen, Weiwei Fu, Jianping Wang

引用次数: 0

Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models. Argus：利用多视图图像来提高对大型语言模型的3d场景理解。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-25 DOI: 10.1109/tnnls.2025.3581411

Yifan Xu,Chao Zhang,Hanqi Jiang,Xiaoyan Wang,Ruifei Ma,Yiwei Li,Zihao Wu,Zeju Li,Xiangde Liu

{"title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models.","authors":"Yifan Xu,Chao Zhang,Hanqi Jiang,Xiaoyan Wang,Ruifei Ma,Yiwei Li,Zihao Wu,Zeju Li,Xiangde Liu","doi":"10.1109/tnnls.2025.3581411","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3581411","url":null,"abstract":"Advancements in foundation models have made it possible to conduct applications in various downstream tasks. Especially, the new era has witnessed a remarkable capability to extend large language models (LLMs) for tackling tasks of 3-D scene understanding. Current methods rely heavily on 3-D point clouds, but the 3-D point cloud reconstruction of an indoor scene often results in information loss. Some textureless planes or repetitive patterns are prone to omission and manifest as voids within the reconstructed 3-D point clouds. Besides, objects with complex structures tend to introduce distortion of details caused by misalignments between the captured images and the dense reconstructed point clouds. The 2-D multiview images present visual consistency with 3-D point clouds and provide more detailed representations of scene components, which can naturally compensate for these deficiencies. Based on these insights, we propose Argus, a novel 3-D multimodal framework that leverages multiview images for enhanced 3-D scene understanding with LLMs. In general, Argus can be treated as a 3-D large multimodal foundation model (3D-LMM) since it takes various modalities as input (text instructions, 2-D multiview images, and 3-D point clouds) and expands the capability of LLMs to tackle 3-D tasks. Argus involves fusing and integrating multiview images and camera poses into view-as-scene features, which interact with the 3-D features to create comprehensive and detailed 3-D-aware scene embeddings. Our approach compensates for the information loss while reconstructing 3-D point clouds and helps LLMs better understand the 3-D world. Extensive experiments demonstrate that our method outperforms existing 3D-LMMs in various downstream tasks.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"21 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144488042","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

Draw What You Hear: High-Fidelity Image Generation and Manipulation via SoundAdapter. 绘制你听到的：高保真图像生成和操作通过SoundAdapter。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-25 DOI: 10.1109/tnnls.2025.3581455

Mingjie Wang,Song Yuan,Xian-Feng Han,Zili Yi

{"title":"Draw What You Hear: High-Fidelity Image Generation and Manipulation via SoundAdapter.","authors":"Mingjie Wang,Song Yuan,Xian-Feng Han,Zili Yi","doi":"10.1109/tnnls.2025.3581455","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3581455","url":null,"abstract":"Currently, the text-to-image (T2I) generation has established itself as a cornerstone within the realm of AI-generated content (AIGC), due its remarkable success to the availability of extensive datasets comprising paired text-vision samples. Nevertheless, the absence of audio-visual pairs hinders the growth of audio-to-image (A2I). Although prior approaches have pioneered the A2I task, the tight entanglement between initial audio and image encoders imposes the challenge of gathering audio-visual samples, resulting in degraded performance and limited sound flexibility. Therefore, this article proposes a novel SoundAdapter to draw what you hear. Specifically, the SoundAdapter's structure is meticulously designed around transformer blocks, which are critical for capturing overarching patterns and dependencies within the data. In addition, it integrates a sophisticated multigranularity approach coupled with a hybrid supervisory signal, ensuring both fine-grained semantic alignment and seamless optimization across various levels of representation. Extensive tests demonstrate that the SoundAdapter excels in training, setting new benchmarks in zero-shot audio classification, as well as in creating and modifying images across a variety of datasets. The implementation code and several demos supporting this study are openly accessible at https://github.com/CV-MM-Lab/SoundAdapter, facilitating reproducibility and further research.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"55 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144488046","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

Generating Simple Cyclic Memristive Neural Network Circuit With Controllable Multiscroll Attractors and Multivariable Amplitude Control. 生成具有可控多涡旋吸引子和多变量幅值控制的简单循环记忆神经网络电路。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-24 DOI: 10.1109/tnnls.2025.3581229

Qiang Lai,Yudi Xu,Luigi Fortuna

{"title":"Generating Simple Cyclic Memristive Neural Network Circuit With Controllable Multiscroll Attractors and Multivariable Amplitude Control.","authors":"Qiang Lai,Yudi Xu,Luigi Fortuna","doi":"10.1109/tnnls.2025.3581229","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3581229","url":null,"abstract":"Due to their synaptic-like characteristics and memory properties, memristors are often used in neuromorphic circuits, particularly neural network circuits. However, most of the existing neural network circuits that can generate complex dynamics have high dimensions and excessive connections, which is not conducive to implementation. This article introduces a memristor containing an arctangent function into a simple cyclic neural network (SCNN) circuit to design a simple cyclic memristive neural network (SCMNN) circuit capable of generating complex multiscroll chaotic attractors. The designed SCMNN contains an external stimulus current and generates multiscroll attractors, with the number of scrolls expanding as the switches in the memristor equivalent circuit are activated. By varying the parameters, the multiscroll attractors can be broken into different numbers of coexisting attractors, which also depends on the switch, and it can achieve multivariable amplitude control when there is only one scroll. The anti-interference ability of the circuit is tested. A low-cost circuit-based microcontroller suitable for engineering applications is designed for it, and multiscroll attractors are successfully captured in an oscilloscope. The National Institute of Standards and Technology (NIST) test is carried out to verify its application value.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"248 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144478769","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

Counterfactual Explanation Through Latent Adjustment in Disentangled Space of Diffusion Model. 扩散模型解纠缠空间的潜调整反事实解释。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-24 DOI: 10.1109/tnnls.2025.3580118

Seung-Hyup Na,Seong-Whan Lee

{"title":"Counterfactual Explanation Through Latent Adjustment in Disentangled Space of Diffusion Model.","authors":"Seung-Hyup Na,Seong-Whan Lee","doi":"10.1109/tnnls.2025.3580118","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3580118","url":null,"abstract":"With the rise of explainable artificial intelligence (XAI), counterfactual (CF) explanations have gained significant attention. Effective CFs must be valid (classified as the CF class), practical (minimally deviated from the input), and plausible (close to the CF data manifold). However, practicality and plausibility often conflict, making valid CF generation challenging. To address this, we propose a novel framework that generates CFs by adjusting only semantic information in the disentangled latent space of a diffusion model. This shifts the sample closer to the CF manifold and across the decision boundary. In our framework, the latent vector mapping step occasionally produces invalid CFs or CFs insufficiently close to the decision boundary, resulting in dissimilarity to the input. Our method overcomes this with a two-stage latent vector adjustment: 1) linear interpolation and 2) time-step-wise optimization during reverse diffusion within the space accommodating linear changes in class information from the input. Experiments demonstrate that our approach generates more valid, plausible, and practical CFs by effectively leveraging the properties of the disentangled latent space.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"46 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144478734","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

New WTOD Protocol-Based Fault Detection Filter Design for Interval Type-2 Fuzzy Systems via an Adaptive Differential Evolution Algorithm. 基于WTOD协议的区间2型模糊系统自适应差分进化故障检测滤波器设计。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-06-24 DOI: 10.1109/tnnls.2025.3579254

Wei Qian,Yanmin Wu,Zidong Wang

{"title":"New WTOD Protocol-Based Fault Detection Filter Design for Interval Type-2 Fuzzy Systems via an Adaptive Differential Evolution Algorithm.","authors":"Wei Qian,Yanmin Wu,Zidong Wang","doi":"10.1109/tnnls.2025.3579254","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3579254","url":null,"abstract":"This article is concerned with the design problem of an $H_{infty }$ optimal fault detection (FD) filter for networked interval type-2 (IT2) fuzzy systems that are subjected to stochastic cyberattacks. To effectively reduce the utilization of constrained network resources, a new dynamically adjusted event-triggered weighted try-once-discard (DAET-WTOD) protocol is developed, in which two adaptive rules are constructed based on the measured output and the probability of denial-of-service (DoS) attacks. Furthermore, a fuzzy switched-like FD filter is designed with the purpose of detecting system fault signals, while simultaneously considering the DAET-WTOD protocol and stochastic cyberattacks. Subsequently, by utilizing an imperfect premise matching (IPM) scheme, an opposition-based learning adaptive differential evolution algorithm is proposed to deal with the networked IT2 fuzzy systems. This algorithm is capable of iteratively searching the membership function values of the fuzzy filter in real time, thereby achieving improved $H_{infty }$ performance. Finally, some simulation results are provided to verify the feasibility and advantages of the proposed $H_{infty }$ optimal FD technique.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"25 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144478790","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