Neurocomputing最新文献

Incorporating edge sharpening and covariance attention for named entity recognition 结合边缘锐化和协方差注意的命名实体识别

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-16 DOI: 10.1016/j.neucom.2025.130402

Caiwei Yang, Yanping Chen, Shuai Yu, Ruizhang Huang, Yongbin Qin

{"title":"Incorporating edge sharpening and covariance attention for named entity recognition","authors":"Caiwei Yang, Yanping Chen, Shuai Yu, Ruizhang Huang, Yongbin Qin","doi":"10.1016/j.neucom.2025.130402","DOIUrl":"10.1016/j.neucom.2025.130402","url":null,"abstract":"<div><div>Named Entity Recognition (NER) is a key application in the field of Artificial Intelligence and Natural Language Processing, which automatically identifies and categorizes entities in text by intelligent algorithms. In NER, all spans of a sentence can be organized into a two-dimensional representation. The semantic plane has the advantage to represent the semantic structure of a sentence and to learn the interaction between spans. One of an important phenomenon of this representation is that neighboring elements of the semantic plane are spans denoted to overlapped subsequences in a sentence. Because they share the same contextual features and semantic dependencies, it is difficult to distinguish true entities from the backgrounds. Therefore, refining span representations and building the semantic dependency between spans is helpful for the entity recognition task. In this paper, we propose an Edge Sharpening and Covariance Attention (ES&CA) model to support recognizing named entities from the semantic plane representation. The edge sharpening (ES) module adopts a differential convolution to sharpen the semantic gradients in the semantic plane, which has the ability to gather semantic information from neighborhoods. In the covariance attention (CA) module, the covariance between spans are applied to weight the attention of spans relevant to task-relevant learning objective. Establishing semantic relationships across spans is a highly successful approach. The ES&CA model is assessed on five public datasets for nested and flattened named entity recognition. The evaluation results demonstrate the effectiveness of our strategy in distinguishing entity spans from the backgrounds, hence significantly enhancing the final performance.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130402"},"PeriodicalIF":5.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Population-Based Meta-Heuristic Optimization Algorithm Booster: An Evolutionary and Learning Competition Scheme 基于群体的元启发式优化算法助推器：一种进化学习竞争方案

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-16 DOI: 10.1016/j.neucom.2025.130405

Jun Wang , Junyu Dong , Huiyu Zhou , Xinghui Dong

{"title":"Population-Based Meta-Heuristic Optimization Algorithm Booster: An Evolutionary and Learning Competition Scheme","authors":"Jun Wang , Junyu Dong , Huiyu Zhou , Xinghui Dong","doi":"10.1016/j.neucom.2025.130405","DOIUrl":"10.1016/j.neucom.2025.130405","url":null,"abstract":"<div><div>In a Population-Based Meta-Heuristic Optimization Algorithm (PMOA), individuals in the population will constantly generate new promising individuals, to form new populations. Although the population continuously changes, the variations in each individual are traceable in most algorithms. An individual in the population comes from the individual in the previous population. The direction of the evolution of populations can be identified on top of this historical inheritance relationship, which improves the efficiency of PMOAs and solves optimization problems more effectively. Since Recurrent Neural Networks (RNNs) are able to capture the temporal dependencies in sequences, we are motivated to propose a novel but simple Evolutionary and Learning Competition Scheme (ELCS), also referred to as the PMOA Booster, in which individuals keep changing for the better fitness based on the heuristic rules of the PMOA while an RNN is used to learn the process that each individual changes in order to guide the generation of promising individuals. The ELCS automatically selects the RNN or PMOA which generates more individuals with the better fitness. We test the proposed scheme using the benchmark of IEEE Congress on Evolutionary Computation 2022 competition (CEC 2022). The results show that this scheme is able to boost the performance of both the classical and state-of-the-art PMOAs and outperforms its counterparts. Also, the ELCS produces promising results in two real-world industrial scenarios. We believe that the effectiveness of the proposed ELCS is due to the adaptive competition between the RNN and the PMOA.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130405"},"PeriodicalIF":5.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Efficient incremental model reduction approach for time-varying spatially distributed processes 时变空间分布过程的有效增量模型约简方法

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-16 DOI: 10.1016/j.neucom.2025.130390

Ai Ling , Hao Ru , Xueqin Chen , Kok Lay Teo

{"title":"Efficient incremental model reduction approach for time-varying spatially distributed processes","authors":"Ai Ling , Hao Ru , Xueqin Chen , Kok Lay Teo","doi":"10.1016/j.neucom.2025.130390","DOIUrl":"10.1016/j.neucom.2025.130390","url":null,"abstract":"<div><div>The accurate and efficient modeling of complex spatially distributed processes (SDPs) represents a significant challenge for researchers in the field. A variety of modeling approaches have been developed with the objective of addressing issues related to spatiotemporal modeling. The conventional offline modeling approaches necessitate the availability of a spatiotemporal data set that encompasses the entirety of the system’s dynamic features. It is not possible to fully satisfy this prerequisite in the context of real-world applications, particularly in the case of time-varying SDPs. Furthermore, the process of updating the model by repeatedly applying the offline algorithm is inherently time-consuming. In this paper, we put forth an efficient incremental model reduction approach for time-varying SDPs. Following the initialization phase, the modified Gram–Schmidt orthogonalization method is employed to extract the feature subspace in a sequential manner. The time-space synthesis is then utilized to reconstruct the spatiotemporal dynamics. The efficacy of the model is evaluated on a representative diffusion-reaction process, and the comparative experimental outcomes demonstrate that the presented algorithm is an efficient and effective approach for the online learning of time-varying SDPs.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130390"},"PeriodicalIF":5.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Vision transformers on the edge: A comprehensive survey of model compression and acceleration strategies 边缘上的视觉变形：模型压缩和加速策略的综合调查

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-16 DOI: 10.1016/j.neucom.2025.130417

Shaibal Saha, Lanyu Xu

{"title":"Vision transformers on the edge: A comprehensive survey of model compression and acceleration strategies","authors":"Shaibal Saha, Lanyu Xu","doi":"10.1016/j.neucom.2025.130417","DOIUrl":"10.1016/j.neucom.2025.130417","url":null,"abstract":"<div><div>In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which rely on hierarchical feature extraction, ViTs treat images as sequences of patches and leverage self-attention mechanisms. However, their high computational complexity and memory demands pose significant challenges for deployment on resource-constrained edge devices. To address these limitations, extensive research has focused on model compression techniques and hardware-aware acceleration strategies. Nonetheless, a comprehensive review that systematically categorizes these techniques and their trade-offs in accuracy, efficiency, and hardware adaptability for edge deployment remains lacking. This survey bridges this gap by providing a structured analysis of model compression techniques, software tools for inference on edge, and hardware acceleration strategies for ViTs. We discuss their impact on accuracy, efficiency, and hardware adaptability, highlighting key challenges and emerging research directions to advance ViT deployment on edge platforms, including graphics processing units (GPUs), application-specific integrated circuit (ASICs), and field-programmable gate arrays (FPGAs). The goal is to inspire further research with a contemporary guide on optimizing ViTs for efficient deployment on edge devices.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130417"},"PeriodicalIF":5.5,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 fMRI time-varying functional connectivity analysis using multivariate swarm decomposition 基于多元群分解的鲁棒fMRI时变功能连通性分析

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130404

Charalampos Lamprou , Georgios Apostolidis , Aamna Alshehhi , Leontios J. Hadjileontiadis , Mohamed L. Seghier

{"title":"Robust fMRI time-varying functional connectivity analysis using multivariate swarm decomposition","authors":"Charalampos Lamprou , Georgios Apostolidis , Aamna Alshehhi , Leontios J. Hadjileontiadis , Mohamed L. Seghier","doi":"10.1016/j.neucom.2025.130404","DOIUrl":"10.1016/j.neucom.2025.130404","url":null,"abstract":"<div><div>Time-varying functional connectivity (TVFC) measured with functional MRI (fMRI) captures dynamic changes in statistical dependencies among regional time series, which can be studied with instantaneous phase synchronization analyses. Phase extraction requires narrow-banded resting-state fMRI (rs-fMRI) data typically extracted with conventional band-pass filtering or advanced mode decomposition techniques. However, filtering methods often struggle to eliminate noise effectively, require prior knowledge of cutoff frequencies, and fail to account for non-stationarity in the data. Likewise, existing mode decomposition techniques strongly depend on input parameters and are less reliable for multivariate analyses. Here, we introduce multivariate swarm decomposition (MSwD), a bio-inspired signal decomposition technique that combines the iterative nature of empirical methods with a robust mathematical foundation. Using synthetic signals and real rs-fMRI data from the Human Connectome Project and the Autism Brain Imaging Data Exchange I, we showed that MSwD-based PS (MSwD-PS) outperforms four state-of-the-art decomposition techniques in several key areas: (1) being more robust to input parameters and better at detecting true synchronizations, showing a 3–65% lower normalized root mean square error in simulated data and being 15.8-73.1% less prone to identifying short biologically implausible transitions between brain states, and (2) showing a reduced likelihood of false positives, being less affected by spurious synchronizations. Likewise, MSwD-informed functional connectivity analysis improved subject fingerprinting and autism spectrum disorder classification using graph neural networks. Overall, MSwD-PS can reduce the risk of false positives in TVFC, which could be extremely useful for processing rs-fMRI data with unknown ground truth in diverse clinical populations.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"642 ","pages":"Article 130404"},"PeriodicalIF":5.5,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A review of Zeroing neural network: Theory, algorithm and application 归零神经网络：理论、算法及应用综述

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130425

Shaoting Cao , Jie Jin , Daobing Zhang , Chaoyang Chen

{"title":"A review of Zeroing neural network: Theory, algorithm and application","authors":"Shaoting Cao , Jie Jin , Daobing Zhang , Chaoyang Chen","doi":"10.1016/j.neucom.2025.130425","DOIUrl":"10.1016/j.neucom.2025.130425","url":null,"abstract":"<div><div>As a powerful method for solving complex computational equations, neural networks have attracted widespread attention due to their unique advantages. However, due to the existence of time-varying problems in practical applications, traditional Gradient neural network (GNN) models may not be able to satisfy the requirements for accurately solving such problems, leading to the emergence of a dynamic system solution method - Zeroing neural network (ZNN), a dynamic system solver designed specifically for solving various time-varying mathematical problems and real-time control applications. ZNN eliminates errors through the use of dynamic differential equations, fundamentally overcoming the limitations of GNN in effectively converging for time-varying problems. Additionally, considering different application demands in practical scenarios and interference from noise in realistic environments, various robust ZNN models with different convergence properties have emerged. This paper will summarize the development of ZNN models in recent years from theoretical foundation, algorithm improvement and practical application aspects, and finally prospect the future research directions of ZNN models to provide researchers with a systematic reference.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130425"},"PeriodicalIF":5.5,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Modeling of distributed parameter systems based on independent partial derivative-physics-informed neural network 基于独立偏导数-物理信息神经网络的分布参数系统建模

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130396

Lijie Wang , Yangshu Lin , Xinrong Yan , Yuhao Shao , Zuhua Xu , Chao Yang , Haidong Fan , Yurong Xie , Chenghang Zheng

{"title":"Modeling of distributed parameter systems based on independent partial derivative-physics-informed neural network","authors":"Lijie Wang , Yangshu Lin , Xinrong Yan , Yuhao Shao , Zuhua Xu , Chao Yang , Haidong Fan , Yurong Xie , Chenghang Zheng","doi":"10.1016/j.neucom.2025.130396","DOIUrl":"10.1016/j.neucom.2025.130396","url":null,"abstract":"<div><div>Physics-informed neural networks (PINNs) have attracted considerable interest due to their capacity to incorporate established physical principles, thus facilitating efficient training with a limited amount of observed data. This approach ensures that the results of supervised learning are in accordance with the governing physical laws of the system, thereby enhancing the interpretability of models. However, existing research predominantly employs a single network architecture to simultaneously learn the information of the partial differential equations (PDEs). Such architectures typically require large network sizes to learn the system characteristics, which leads to prolonged training times and inefficiencies. This paper introduces a novel modeling framework, termed the independent partial derivative-physics-informed neural network (IPD-PINN). In contrast to conventional methodologies, IPD-PINN employs a network comprising multiple subnetworks, with each subnetwork dedicated to the learning of individual partial derivatives in the PDEs. The modular network structure allows for flexible and scalable adjustments to the size of each subnetwork, accommodating modeling tasks of varying complexities. Consequently, the entire network is capable of reducing the required training time while maintaining precise modeling accuracy. The efficacy of the proposed IPD-PINN method is demonstrated through two simulation case studies, which highlight its potential to improve the efficiency and accuracy of IPD-PINN modeling.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"642 ","pages":"Article 130396"},"PeriodicalIF":5.5,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A dual-branch deep interaction network for multi-channel speech enhancement 一种用于多通道语音增强的双分支深度交互网络

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130412

Xiaoyu Lian, Nan Xia, Gaole Dai, Hongqin Yang

引用次数: 0

Spatio-temporal prediction using graph neural networks: A survey 基于图神经网络的时空预测研究进展

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130400

Vincenzo Capone, Angelo Casolaro, Francesco Camastra

{"title":"Spatio-temporal prediction using graph neural networks: A survey","authors":"Vincenzo Capone, Angelo Casolaro, Francesco Camastra","doi":"10.1016/j.neucom.2025.130400","DOIUrl":"10.1016/j.neucom.2025.130400","url":null,"abstract":"<div><div>The analysis of spatial time series is increasingly relevant as spatio-temporal data are becoming widespread due to the ever-growing diffusion of data acquisition devices. Spatio-temporal prediction is crucial for grasping insights on spatio-temporal dynamics in diverse domains. In many cases, spatio-temporal data can be effectively represented using graphs, thus making Graph Neural Networks the most sounding deep learning architecture for the modelling of spatio-temporal series. The aim of the work is to provide a self-consistent and thorough overview on Graph Neural Networks for spatio-temporal prediction, giving a taxonomy of the diverse approaches proposed in the literature. Moreover, attention is paid to the description of the most used benchmarks and metrics in different real-world spatio-temporal domains and to the discussion of the main drawbacks of spatio-temporal Graph Neural Networks. Furthermore, unlike other similar works on deep learning, statistical methods for spatio-temporal modelling are briefly surveyed in this work. Finally, insights on future developments of Graph Neural Networks for spatio-temporal prediction are suggested.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130400"},"PeriodicalIF":5.5,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Universality conditions of unified classical and quantum reservoir computing 统一经典和量子库计算的通用性条件

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-05-15 DOI: 10.1016/j.neucom.2025.130391

Francesco Monzani, Enrico Prati

{"title":"Universality conditions of unified classical and quantum reservoir computing","authors":"Francesco Monzani, Enrico Prati","doi":"10.1016/j.neucom.2025.130391","DOIUrl":"10.1016/j.neucom.2025.130391","url":null,"abstract":"<div><div>Reservoir computing is a versatile paradigm in computational neuroscience and machine learning, that exploits a recurrent neural network to efficiently process time-dependent information. The power of many neural network architectures resides in their universality approximation property. As widely known, classes of reservoir computers serve as universal approximators of functionals with fading memory. The construction of such universal classes often appears context-specific, but, in fact, they follow the same principles. Here we present a unified theoretical framework and we propose a ready-made setting to secure universality, based on the minimal sufficient conditions for a class of reservoir computers to be universal, namely the fading memory and the polynomial algebra structure of the set of their associated functionals. We test the result in the arising context of quantum reservoir computing. Guided by such a unified theorem we suggest why spatial multiplexing serves as a computational resource when dealing with quantum registers, as empirically observed in specific implementations on quantum hardware. The analysis sheds light on a unified view of classical and quantum reservoir computing.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"643 ","pages":"Article 130391"},"PeriodicalIF":5.5,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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