arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

IEEE TNNLS

IEEE Transactions on Neural Networks and Learning Systems · 期刊 · Machine Learning

共收录 672
2501.08096 2026-03-31 cs.RO cs.AI cs.ET cs.LG

Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving

基于混合动作的多目标兼容自动驾驶强化学习

Guizhe Jin, Zhuoren Li, Bo Leng, Wei Han, Lu Xiong, Chen Sun

机构 * College of Automotive and Energy Engineering, Tongji University(同济大学汽车与能源工程学院) Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系)

AI总结 本文提出一种多目标集成-批评强化学习方法,通过混合参数化动作空间结构和不确定性探索机制,提升自动驾驶在多目标兼容性、效率和安全性方面的性能。

Comments 14 pages, accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.05352 2026-03-31 cs.LG cs.AI

Recent Advances of Multimodal Continual Learning: A Comprehensive Survey

多模态持续学习的最新进展:综合性综述

Dianzhi Yu, Xinni Zhang, Yankai Chen, Aiwei Liu, Yifei Zhang, Philip S. Yu, Irwin King

机构 * Tsinghua University(清华大学) University of Illinois Chicago(伊利诺伊大学芝加哥分校)

AI总结 本文综述了多模态持续学习的最新进展,分析了其核心挑战与方法分类,提出四种主要方法类别,并讨论了未来研究方向和开放资源。

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS). DOI: 10.1109/TNNLS.2026.3658485. Copyright 2026 IEEE

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26489 2026-03-30 astro-ph.IM astro-ph.CO cs.LG

Conditional Neural Bayes Ratio Estimation for Experimental Design Optimisation

基于条件神经贝叶斯比率估计的实验设计优化

S. A. K. Leeney, T. Gessey-Jones, W. J. Handley, E. de Lera Acedo, H. T. J. Bevins, J. L. Tutt

机构 * Cavendish Astrophysics, University of Cambridge(剑桥大学卡文迪什天体物理学) Kavli Institute for Cosmology, University of Cambridge(剑桥大学卡夫利宇宙学研究所) PhysicsX Institute of Astronomy, University of Cambridge(剑桥大学天文学研究所)

AI总结 本文提出条件神经贝叶斯比率估计方法,用于在边缘可探测条件下优化实验设计,通过连续设计空间探索提升发现概率预测效率。

Comments 11 pages, 5 figures. Submitted to IEEE Transactions on Neural Networks and Learning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.18655 2026-03-20 cs.CV cs.AI

Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation

多尺度开关用于医学超声图像分割中的半监督和对比学习

Jingguo Qu, Xinyang Han, Yao Pu, Man-Lik Chui, Simon Takadiyi Gunda, Ziman Chen, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying

机构 * Department of Health Technology and Informatics, The Hong Kong Polytechnic University(健康科技与信息学系,香港理工大学) Centre for Smart Health and School of Nursing, The Hong Kong Polytechnic University(智能健康中心及护理学院,香港理工大学) Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong(影像与介入放射科,香港中文大学)

AI总结 本文提出Switch框架,通过多尺度开关和频域开关提升医学超声图像分割的半监督和对比学习效果,在低标注率下取得显著Dice系数提升。

Comments This is the author-submitted LaTeX version with original typesetting. The final published version (with IEEE production formatting and layout changes) is available at http://doi.org/10.1109/TNNLS.2026.3669814 under CC BY 4.0 license

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02970 2026-03-19 math.OC

A Fully Data-Driven Value Iteration for Stochastic LQR: Convergence, Robustness and Stability

一种完全数据驱动的价值迭代用于随机线性二次控制:收敛性、鲁棒性和稳定性

Leilei Cui, Zhong-Ping Jiang, Petter N. Kolm, Grégoire G. Macqueron

AI总结 本文研究了数据驱动控制中价值迭代算法在随机线性二次系统中的收敛性、鲁棒性和稳定性,提出无需初始控制策略的鲁棒自适应动态规划算法,并通过数据中心冷却和动态投资组合分配实验验证其有效性。

Comments To be published in IEEE Transactions on Neural Networks and Learning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.18981 2026-03-13 cs.LG cs.AI

FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classification

FedSKD: 一种无需聚合的联邦学习模型异质性方法通过多维相似性知识蒸馏用于医学图像分类

Ziqiao Weng, Weidong Cai, Bo Zhou

AI总结 FedSKD通过多维相似性知识蒸馏实现无需聚合的异构联邦学习,提升医学图像分类的个性化与泛化能力。

Comments Accepted at IEEE-TNNLS, 17 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11056 2026-03-13 cs.NE

GeNeX: Genetic Network eXperts framework for addressing Validation Overfitting

GeNeX:用于解决验证过拟合的遗传网络专家框架

Emmanuel Pintelas, Ioannis E. Livieris

AI总结 GeNeX通过遗传算法和双路径策略缓解验证过拟合,生成鲁棒模型并构建互补集成,提升模型泛化能力。

Comments Accepted for publication in IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

Journal ref IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22302 2026-03-09 cs.LG cs.CR cs.DC

ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning

ZK-HybridFL:零知识证明增强的混合账本用于联邦学习

Amirhossein Taherpour, Xiaodong Wang

机构 * Electrical Engineering Department, Columbia University(哥伦比亚大学电气工程系)

AI总结 ZK-HybridFL通过整合DAG账本、侧链和零知识证明,实现隐私保护的分布式联邦学习,提升模型训练效率和安全性。

Comments Accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00710 2026-03-03 cs.LG cs.NE

Reward-Modulated Local Learning in Spiking Encoders: Controlled Benchmarks with STDP and Hybrid Rate Readouts

基于奖励调节的局部学习在脉冲编码器中的应用:STDP与混合速率读出的受控基准

Debjyoti Chakraborty

AI总结 本文提出了一种基于奖励调节的局部学习方法,通过STDP和混合速率读出在手写数字识别中实现了较高的准确率,并探讨了奖励塑造对模型性能的影响。

Comments 10 pages, 5 figures. Submitted to IEEE Transactions on Neural Networks and Learning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.17028 2026-02-20 cs.LG cs.AI

Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles

通过不确定性感知的时间序列集成预测异常前兆

Hyeongwon Kang, Jinwoo Park, Seunghun Han, Pilsung Kang

机构 * Department of Industrial & Management Engineering, Korea University(韩国大学工业与管理工程系) Department of Industrial Engineering, Seoul National University(首尔国立大学工业工程系) LG CNS

AI总结 FATE通过不确定性感知的时间序列集成方法,有效检测异常前兆,无需异常标签,在多个数据集上取得显著提升。

Comments This manuscript contains 14 pages and 8 figures. It is currently under review at IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.00468 2026-02-19 cs.AI

RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway

RadDQN:一种基于深度Q学习的架构,用于寻找时间高效且辐射暴露最小的路径

Biswajit Sadhu, Trijit Sadhu, S. Anand

机构 * Health Physics Division, Health Safety and Environment Group, Bhabha Atomic Research Center, Mumbai – 400085, India(健康物理学部、健康安全与环境组、Bhabha原子研究中心,印度孟买,400085) Birla Institute of Technology, PILANI, Rajasthan – 333031, India(比拉理工学院,印度帕利尼,拉贾斯坦,333031)

AI总结 RadDQN是一种基于深度Q学习的架构,通过辐射感知奖励函数和优化探索策略,提升无人机在辐射区域中的路径规划效率和辐射防护能力。

Comments 12 pages, 7 main figures, code link (GitHub)

Journal ref IEEE Transactions on Neural Networks and Learning Systems ( Volume: 36, Issue: 9, September 2025), Page(s): 15951 - 15962

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.08513 2026-02-10 cs.NE

A Multi-objective Evolutionary Algorithm Based on Bi-population with Uniform Sampling for Neural Architecture Search

基于双种群与均匀采样的多目标进化算法用于神经架构搜索

Yu Xue, Pengcheng Jiang, Chenchen Zhu, Yong Zhang, Ran Cheng, Kaizhou Gao, Dunwei Gong

AI总结 MOEA-BUS通过双种群与均匀采样方法,提升神经架构搜索中多目标优化的效率与性能。

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems. Published on this https URL: https://doi.org/10.1109/TNNLS.2026.3659508

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.02439 2026-02-03 cs.NE cs.ET cs.LG

Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization

边缘AI的节能类脑计算:一种结合自适应脉冲神经网络和硬件感知优化的框架

Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz, Duygu Erisken, Rana Irem Turhan

机构 * Department of Applied Mathematics and Computer Science (DTU Compute)(应用数学与计算机科学系(DTU计算)) Department of Engineering(工程系) Department of Computer Engineering(计算机工程系) Department of Mathematics(数学系) Department of Computer Systems(计算机系统系)

AI总结 NeuEdge框架通过自适应脉冲神经网络和硬件感知优化,实现边缘AI的超低功耗、低延迟推理,达到高能效和实时性能。

Comments 8 pages, 4 figures, 4 tables. Submitted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21707 2026-01-30 math.NA cs.NA

Adaptive Kernel Methods

自适应核方法

Tamás Dózsa, Andrea Angino, Zoltán Szabó, József Bokor, Matthias Voigt

AI总结 本文提出了一种自适应核方法,通过引入可学习参数来优化解空间,提升大规模问题的处理效率。

Comments Submitted to IEEE Transactions on Neural Networks and Learning Systems for review

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14957 2026-01-29 cs.CV

Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering

用于过程视频问答的神经符号知识推理

Basura Fernando, Thanh-Son Nguyen, Hong Yang, Tzeh Yuan Neoh, Hao Zhang, Ee Yeo Keat

机构 * Centre for Frontier AI Research, A*STAR, Singapore(前沿人工智能研究所以(A*STAR)) Institute of High-Performance Computing, A*STAR, Singapore(高性能计算研究所(A*STAR)) College of Computing and Data Science, NTU, Singapore(计算与数据科学学院(NTU))

AI总结 本文提出KML框架,通过神经符号方法提升过程视频问答的推理能力,结合知识图谱实现可解释的多步骤推理。

Comments This paper is under review at IEEE Transactions on Neural Networks and Learning Systems. Personal use is permitted, but republication/redistribution requires IEEE permission

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.11024 2026-01-28 cs.LG cs.AI

D2Vformer: A Flexible Time Series Prediction Model Based on Time Position Embedding

D2Vformer:基于时间位置嵌入的灵活时间序列预测模型

Xiaobao Song, Hao Wang, Liwei Deng, Yuxin He, Wenming Cao, Chi-Sing Leungc

机构 * Shenzhen University(深圳大学) Shenzhen Technology University(深圳科技大学) City University of Hong Kong(香港城市大学)

AI总结 D2Vformer通过时间位置嵌入和注意力机制,实现了对非相邻和动态长度时间序列的高效预测。

Journal ref IEEE Transactions on Neural Networks and Learning Systems. 2025 1-12

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11638 2026-01-21 cs.LG stat.ML

Verifying Physics-Informed Neural Network Fidelity using Classical Fisher Information from Differentiable Dynamical System

通过可微动力学系统中的经典Fisher信息验证物理信息神经网络的保真度

Josafat Ribeiro Leal Filho, Antônio Augusto Fröhlich

机构 * lisha (Software/Hardware Integration Lab)(lisha(软件/硬件集成实验室))

AI总结 本文提出通过经典Fisher信息验证PINN保真度的方法,利用可微动力学系统分析其在物理建模中的有效性。

Comments This paper has been submitted and is currently under review at IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.07720 2026-01-15 eess.IV cs.CV

Exploiting Scale-Variant Attention for Segmenting Small Medical Objects

利用尺度变异注意力进行小医学物体分割

Wei Dai, Rui Liu, Zixuan Wu, Tianyi Wu, Min Wang, Junxian Zhou, Yixuan Yuan, Jun Liu

机构 * Centre for Robotics and Automation, City University of Hong Kong(香港城市大学机器人与自动化中心) Department of Electronic Engineering, The Chinese University of Hong Kong(香港中文大学电子工程系)

AI总结 本文提出SvANet,通过引入尺度变异注意力等模块,提升医学图像中小物体的分割精度。

Comments 14 pages, 9 figures, under review

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 1-18 (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.09777 2025-12-23 cs.LG cs.AI

Graph Transformers: A Survey

图变换器:综述

Ahsan Shehzad, Feng Xia, Shagufta Abid, Ciyuan Peng, Shuo Yu, Dongyu Zhang, Karin Verspoor

机构 * School of Software, Dalian University of Technology(大连理工大学软件学院) School of Computing Technologies, RMIT University(皇家墨尔本理工大学计算技术学院) Institute of Innovation, Science and Sustainability, Federation University Australia(联邦大学澳大利亚创新、科学与可持续性研究所) School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院) School of Foreign Languages and School of Software Technology, Dalian University of Technology(大连理工大学外语学院和软件技术学院)

AI总结 本文综述了图变换器的研究进展,探讨了其设计、应用及面临的挑战,为未来研究提供了方向。

Comments 21 pages, 4 figures

Journal ref IEEE Transactions on Neural Networks and Learning Systems 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.13410 2025-12-16 cs.LG stat.ML

Multiclass Graph-Based Large Margin Classifiers: Unified Approach for Support Vectors and Neural Networks

多类图基大边距分类器:支持向量和神经网络的统一方法

Vítor M. Hanriot, Luiz C. B. Torres, Antônio P. Braga

机构 * Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais(电气工程联合培养项目,巴西米纳斯吉拉斯联邦大学) Department of Computer and Systems, Universidade Federal de Ouro Preto(计算机与系统系,巴西欧鲁普穆联邦大学)

AI总结 本文提出了一种基于Gabriel图的多类大边距分类器,通过改进支持向量和神经网络结构,提升分类性能。

Comments Accepted to the IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Journal ref IEEE Transactions on Neural Networks and Learning Systems (Volume: 36, Issue: 5, May 2025, Pages: 8307 - 8316)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05515 2025-12-08 cs.CV cs.LG

DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis

DashFusion: 基于分层瓶颈融合的双流对齐多模态情感分析

Yuhua Wen, Qifei Li, Yingying Zhou, Yingming Gao, Zhengqi Wen, Jianhua Tao, Ya Li

机构 * School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院) Beijing National Research Center for Information Science and Technology, Tsinghua University(清华大学信息科学与技术国家研究中心) Department of Automation, Tsinghua University(清华大学自动化系)

AI总结 DashFusion通过双流对齐与分层瓶颈融合技术,提升多模态情感分析的性能与效率。

Comments Accepted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04625 2025-12-05 cs.LG cs.CV

Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective

重新思考解耦知识蒸馏:从预测分布的角度出发

Bowen Zheng, Ran Cheng

机构 * Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University(数据科学与人工智能系,香港理工大学) Department of Computing, The Hong Kong Polytechnic University(计算系,香港理工大学) The Hong Kong Polytechnic University Shenzhen Research Institute(香港理工大学深圳研究院)

AI总结 从预测分布角度重新审视解耦知识蒸馏,提出更灵活的GDKD损失和高效算法,提升知识提取效果。

Comments Accepted to IEEE TNNLS

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.15711 2025-11-27 cs.AI q-bio.NC

Semi-supervised Multimodal Representation Learning through a Global Workspace

通过全局工作空间实现半监督多模态表示学习

Benjamin Devillers, Léopold Maytié, Rufin VanRullen

机构 * CerCo, CNRS UMR 5549, Université de Toulouse and ANITI, Artificial and Natural Intelligence Toulouse Institute(CerCo、CNRS UMR 5549、图卢兹大学和ANITI人工智能与自然智能图卢兹研究所)

AI总结 本文提出了一种受全局工作空间概念启发的神经网络架构,通过自监督学习实现多模态表示对齐与转换,显著减少对匹配数据的需求。

Comments Under review

Journal ref IEEE Transactions on Neural Networks and Learning Systems 36 (5), 7843-7857 (2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.09178 2025-11-26 cs.RO

A Physics-informed Demonstration-guided Learning Framework for Granular Material Manipulation

一种融合物理信息的示范引导学习框架用于颗粒材料操控

Minglun Wei, Xintong Yang, Yu-Kun Lai, Seyed Amir Tafrishi, Ze Ji

机构 * School of Engineering, Cardiff University(工程学院,卡迪夫大学) School of Computer Science and Informatics, Cardiff University(计算机科学与信息学学院,卡迪夫大学)

AI总结 本文提出一种融合物理信息的示范引导学习框架,通过可微分模拟器和梯度优化生成示范,实现高效学习颗粒材料操控任务。

Comments Accepted as a regular paper by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06273 2025-11-11 cs.LG cs.AI

COTN: A Chaotic Oscillatory Transformer Network for Complex Volatile Systems under Extreme Conditions

Boyan Tang, Yilong Zeng, Xuanhao Ren, Peng Xiao, Yuhan Zhao, Raymond Lee, Jianghua Wu

机构 * Shenzhen Research Institute of Big Data(深圳大数据研究院) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)) Guangdong Provincial Key Laboratory of IRADS(广东省IRADS重点实验室) Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science(广东省珠海交叉学科与数据科学应用重点实验室) Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学)

Comments Submitted to IEEE Transactions on Neural Networks and Learning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.18065 2025-11-05 cs.CV cs.AI cs.CL cs.RO

Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation

Ziming Wei, Bingqian Lin, Yunshuang Nie, Jiaqi Chen, Shikui Ma, Hang Xu, Xiaodan Liang

机构 * Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区) Shanghai Jiao Tong University(上海交通大学) The University of Hong Kong(香港大学) Hunan Artificial Intelligence and Robotics Institute Company Ltd.(湖南人工智能与机器人研究院有限公司) Huawei Noah’s Ark Lab(华为诺亚实验室) Peng Cheng Laboratory(鹏城实验室)

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.08525 2025-10-31 cs.LG cs.AI

A mathematical certification for positivity conditions in Neural Networks with applications to partial monotonicity and Trustworthy AI

Alejandro Polo-Molina, David Alfaya, Jose Portela

机构 * CDTI

Comments 16 pages, 4 figures

Journal ref IEEE Transactions on Neural Networks and Learning Systems, Early Access, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22567 2025-10-28 stat.ML cs.LG

Semi-Supervised Learning under General Causal Models

Archer Moore, Heejung Shim, Jingge Zhu, Mingming Gong

Journal ref IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 4, pp. 7345-7356, Apr. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20807 2025-10-24 cs.CV cs.LG

Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers

Dean L Slack, G Thomas Hudson, Thomas Winterbottom, Noura Al Moubayed

机构 * Durham University(杜伦大学)

Comments 14 pages, 14 figures

Journal ref IEEE Transactions on Neural Networks and Learning Systems, 36, 19106-19118, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14467 2025-10-17 cs.RO

Restoring Noisy Demonstration for Imitation Learning With Diffusion Models

Shang-Fu Chen, Co Yong, Shao-Hua Sun

机构 * Graduate Institute of Communication Engineering, National Taiwan University(国立台湾大学通信工程研究所) Data Science Degree Program, National Taiwan University and Academia Sinica(国立台湾大学数据科学学士学位计划) Department of Electrical Engineering, National Taiwan University(国立台湾大学电子工程系)

Comments Published in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Journal ref IEEE Transactions on Neural Networks and Learning Systems (TNNLS), pp. 1-13, Sept. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏