IEEE transactions on neural networks and learning systems最新文献_第5页

DigNet: Digging Clues From Local–Global Interactive Graph for Aspect-Level Sentiment Classification DigNet：从局部-全局交互图中挖掘线索用于方面级情感分类

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-19 DOI: 10.1109/tnnls.2025.3564306

Bowen Xing, Ivor W. Tsang

引用次数: 0

A Robust Three-Way Classifier With Shadowed Granular Balls Based on Justifiable Granularity 基于合理粒度的阴影颗粒球鲁棒三向分类器

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-19 DOI: 10.1109/tnnls.2025.3563889

Jie Yang, Lingyun Xiaodiao, Guoyin Wang, Witold Pedrycz, Shuyin Xia, Qinghua Zhang, Di Wu

引用次数: 0

A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment 多障碍环境下策略导向的强化学习包围圈控制方法

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-16 DOI: 10.1109/tnnls.2025.3566548

Fandi Gou, Haikuo Du, Chenyu Zhao, Yunze Cai

引用次数: 0

Class-Specific Prompt Learning for Vision–Language Models 视觉语言模型的类特定提示学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-16 DOI: 10.1109/tnnls.2025.3566559

Runhao Li, Yongming Chen, Zhenyu Weng, Zhiping Lin, Yap-Peng Tan

引用次数: 0

SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices 资源受限终端设备的自适应联邦持续学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-16 DOI: 10.1109/tnnls.2025.3565827

Zhengyi Zhong, Weidong Bao, Ji Wang, Jianguo Chen, Lingjuan Lyu, Wei Yang Bryan Lim

引用次数: 0

Toward Ultralow-Power Neuromorphic Speech Enhancement With Spiking-FullSubNet 基于峰值-全子网的超低功耗神经形态语音增强研究

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-15 DOI: 10.1109/tnnls.2025.3566021

Xiang Hao, Chenxiang Ma, Qu Yang, Jibin Wu, Kay Chen Tan

引用次数: 0

Milne-Hamming Method With Zeroing Neural Network for Time-Varying Nonlinear Optimization and Redundant Manipulator Application. 带归零神经网络的Milne-Hamming时变非线性优化方法及冗余机械臂应用。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-15 DOI: 10.1109/tnnls.2025.3563991

Ying Kong,Xi Chen,Yunliang Jiang,Danfeng Sun

{"title":"Milne-Hamming Method With Zeroing Neural Network for Time-Varying Nonlinear Optimization and Redundant Manipulator Application.","authors":"Ying Kong,Xi Chen,Yunliang Jiang,Danfeng Sun","doi":"10.1109/tnnls.2025.3563991","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3563991","url":null,"abstract":"Continuous zeroing neural network (ZNN) and its discrete ZNN (DZNN) are comprehensively developed in many optimization systems. In this article, a Milne-Hamming method with DZNN classified as an implicit method is proposed and discussed upon the previous researches. Specifically, the Milne-Hamming discrete ZNN (MHDZNN) model is aimed for time-varying nonlinear optimization (TV-NO) problem with functional limitations. This Milne-Hamming (MH) method is a four-step discretized formula with fixed parameters and is introduced to discretize the ZNN model. Theoretical analyses of the MHDZNN model derive that MHDZNN possesses a larger stepsize domain $mu in (0,1/2)$ of absolute stability. Its convergent error is of order $O(tau ^{5})$ and the corresponding truncation error constant is $1/40$ , which shows intimate relation to the accuracy. Compared with the existing DZNN models such as four-step explicit methods with the same $O(tau ^{5})$ pattern, the convergent error constant of MHDZNN is smaller by a factor and maximal stability domain is greater. Finally, numerical simulations and application to redundant manipulators are provided and studied to verify the effectiveness of the proposed MHDZNN model.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"30 11 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065847","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

Threats and Defenses in the Federated Learning Life Cycle: A Comprehensive Survey and Challenges 联邦学习生命周期中的威胁与防御：综合调查与挑战

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-15 DOI: 10.1109/tnnls.2025.3563537

Yanli Li, Zhongliang Guo, Nan Yang, Huaming Chen, Dong Yuan, Weiping Ding

引用次数: 0

Rapid Dynamical Pattern Classification via Deterministic Learning From Sampling Sequences. 基于采样序列确定性学习的快速动态模式分类。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-15 DOI: 10.1109/tnnls.2025.3565535

Weiming Wu,Zhirui Li,Chen Sun,Cong Wang,Guanrong Chen

{"title":"Rapid Dynamical Pattern Classification via Deterministic Learning From Sampling Sequences.","authors":"Weiming Wu,Zhirui Li,Chen Sun,Cong Wang,Guanrong Chen","doi":"10.1109/tnnls.2025.3565535","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3565535","url":null,"abstract":"This article is concerned with the rapid classification issue for dynamical patterns consisting of sampling sequences in a relatively large-scale dynamical dataset constructed by benchmark Rossler systems. Specifically, based on a recently developed deterministic learning mechanism, a rapid dynamical pattern classification method is developed, which contains a modeling stage and a classification stage. In the modeling stage, a deterministic learning scheme is employed to accurately learn/model the inherent dynamics of the training dynamical patterns and store the acquired knowledge in a set of constant radial basis function (RBF) networks. In the classification stage, based on the trained RBF networks, a set of dynamical estimators is developed for real-time dynamic comparison. The generating recognition errors are then used to effectively represent the dynamic differences in real-time. To this end, the associated class label of the minimum recognition error is assigned to the test pattern also in real-time. To demonstrate the effectiveness of the proposed method, a relatively large-scale dynamical pattern dataset containing various dynamical behaviors is constructed by utilizing a deterministic chaos prospector (DCP) technique. The simulation results show that the new method achieves competitive classification performances compared to the state-of-the-art time-series classification method for the dynamical system classification task. In addition to performance advantages, the new method can perform real-time time-series classification with the first 10% of data achieving over 95% of accuracy based on the full-length data. Besides, the superiority of our method is demonstrated from various datasets in the UCR time-series classification (TSC) archive.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"28 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065849","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

Bi-PIL: Bidirectional Gradient-Free Learning Scheme for Multilayer Neural Networks. Bi-PIL：多层神经网络双向无梯度学习方案。

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2025-05-15 DOI: 10.1109/tnnls.2025.3564654

Ke Wang,Binghong Liu,Pandi Liu,Yungao Shi,Ping Guo,Yafei Li,Mingliang Xu

{"title":"Bi-PIL: Bidirectional Gradient-Free Learning Scheme for Multilayer Neural Networks.","authors":"Ke Wang,Binghong Liu,Pandi Liu,Yungao Shi,Ping Guo,Yafei Li,Mingliang Xu","doi":"10.1109/tnnls.2025.3564654","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3564654","url":null,"abstract":"Training deep neural networks typically relies on gradient descent learning schemes, which is usually time-consuming, and the design of complex network architectures is often intractable. In this article, we explore the building of multilayer neural networks based on an efficient gradient-free learning scheme offering a potential solution to the architectural design. The proposed learning scheme encompasses both forward and backward training (BT) processes. In the forward process, the pseudoinverse learning (PIL) algorithm is employed to train a multilayer neural network, in which the network is dynamically constructed leveraging a layer-by-layer greedy strategy, enabling the automatic determination of the architecture across different hierarchies in a data-driven manner. The network architecture and connection weights determined in the forward training (FT) process are shared with the backward process which also conducts gradient-free learning to update the connection weights. After the bidirectional learning, a neural network comprising two twin subnetworks is obtained, and the fused features of subnetworks are used as inputs for downstream tasks. Comprehensive experiments and detailed analyses demonstrate the effectiveness and superiority of the proposed learning scheme.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"1 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065848","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