IEEE transactions on neural networks and learning systems最新文献_第6页

Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks. 用于结构稀疏贝叶斯神经网络的 "尖峰-板块收缩先验"（Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks）。

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-31 DOI: 10.1109/TNNLS.2024.3485529

Sanket Jantre, Shrijita Bhattacharya, Tapabrata Maiti

{"title":"Spike-and-Slab Shrinkage Priors for Structurally Sparse Bayesian Neural Networks.","authors":"Sanket Jantre, Shrijita Bhattacharya, Tapabrata Maiti","doi":"10.1109/TNNLS.2024.3485529","DOIUrl":"10.1109/TNNLS.2024.3485529","url":null,"abstract":"Network complexity and computational efficiency have become increasingly significant aspects of deep learning. Sparse deep learning addresses these challenges by recovering a sparse representation of the underlying target function by reducing heavily overparameterized deep neural networks. Specifically, deep neural architectures compressed via structured sparsity (e.g., node sparsity) provide low-latency inference, higher data throughput, and reduced energy consumption. In this article, we explore two well-established shrinkage techniques, Lasso and Horseshoe, for model compression in Bayesian neural networks (BNNs). To this end, we propose structurally sparse BNNs, which systematically prune excessive nodes with the following: 1) spike-and-slab group Lasso (SS-GL) and 2) SS group Horseshoe (SS-GHS) priors, and develop computationally tractable variational inference, including continuous relaxation of Bernoulli variables. We establish the contraction rates of the variational posterior of our proposed models as a function of the network topology, layerwise node cardinalities, and bounds on the network weights. We empirically demonstrate the competitive performance of our models compared with the baseline models in prediction accuracy, model compression, and inference latency.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142557731","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

Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations. 具有交互和任务表征的多任务多代理强化学习

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-30 DOI: 10.1109/TNNLS.2024.3475216

Chao Li, Shaokang Dong, Shangdong Yang, Yujing Hu, Tianyu Ding, Wenbin Li, Yang Gao

{"title":"Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations.","authors":"Chao Li, Shaokang Dong, Shangdong Yang, Yujing Hu, Tianyu Ding, Wenbin Li, Yang Gao","doi":"10.1109/TNNLS.2024.3475216","DOIUrl":"https://doi.org/10.1109/TNNLS.2024.3475216","url":null,"abstract":"Multi-task multi-agent reinforcement learning (MT-MARL) is capable of leveraging useful knowledge across multiple related tasks to improve performance on any single task. While recent studies have tentatively achieved this by learning independent policies on a shared representation space, we pinpoint that further advancements can be realized by explicitly characterizing agent interactions within these multi-agent tasks and identifying task relations for selective reuse. To this end, this article proposes Representing Interactions and Tasks (RIT), a novel MT-MARL algorithm that characterizes both intra-task agent interactions and inter-task task relations. Specifically, for characterizing agent interactions, RIT presents the interactive value decomposition to explicitly take the dependency among agents into policy learning. Theoretical analysis demonstrates that the learned utility value of each agent approximates its Shapley value, thus representing agent interactions. Moreover, we learn task representations based on per-agent local trajectories, which assess task similarities and accordingly identify task relations. As a result, RIT facilitates the effective transfer of interaction knowledge across similar multi-agent tasks. Structurally, RIT develops universal policy structure for scalable multi-task policy learning. We evaluate RIT against multiple state-of-the-art baselines in various cooperative tasks, and its significant performance under both multi-task and zero-shot settings demonstrates its effectiveness.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142545189","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

IEEE Transactions on Neural Networks and Learning Systems Publication Information 电气和电子工程师学会神经网络与学习系统论文集》（IEEE Transactions on Neural Networks and Learning Systems）出版信息

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/TNNLS.2024.3478713

引用次数: 0

Partition-Level Tensor Learning-Based Multiview Unsupervised Feature Selection 基于分区级张量学习的多视角无监督特征选择

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/tnnls.2024.3482440

Zhiwen Cao, Xijiong Xie

引用次数: 0

IEEE Computational Intelligence Society Information 电气和电子工程师学会计算智能学会信息

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/TNNLS.2024.3478709

引用次数: 0

Spectral Super-Resolution in Frequency Domain 频域光谱超分辨率

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/tnnls.2024.3481060

Puhong Duan, Tianci Shan, Xudong Kang, Shutao Li

引用次数: 0

IEEE Transactions on Neural Networks and Learning Systems Information for Authors IEEE 神经网络与学习系统论文集作者须知

IF 10.2 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/TNNLS.2024.3478711

引用次数: 0

Reinforcement Learning-Based Nonautoregressive Solver for Traveling Salesman Problems 基于强化学习的旅行推销员问题非自回归求解器

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/tnnls.2024.3483231

Yubin Xiao, Di Wang, Boyang Li, Huanhuan Chen, Wei Pang, Xuan Wu, Hao Li, Dong Xu, Yanchun Liang, You Zhou

引用次数: 0

Asymmetrical Contrastive Learning Network via Knowledge Distillation for No-Service Rail Surface Defect Detection 通过知识提炼实现非对称对比学习网络，用于无服务铁路表面缺陷检测

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/tnnls.2024.3479453

Wujie Zhou, Xinyu Sun, Xiaohong Qian, Meixin Fang

引用次数: 0

Historical Decision-Making Regularized Maximum Entropy Reinforcement Learning 历史决策正则化最大熵强化学习

IF 10.4 1区计算机科学

IEEE transactions on neural networks and learning systems Pub Date : 2024-10-29 DOI: 10.1109/tnnls.2024.3481887

Botao Dong, Longyang Huang, Ning Pang, Hongtian Chen, Weidong Zhang

引用次数: 0