Neural Networks最新文献_第2页

Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-15 DOI: 10.1016/j.neunet.2025.107257

Xiasheng Shi , Jian Liu , Changyin Sun

引用次数: 0

Don’t fear peculiar activation functions: EUAF and beyond

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-14 DOI: 10.1016/j.neunet.2025.107258

Qianchao Wang , Shijun Zhang , Dong Zeng , Zhaoheng Xie , Hengtao Guo , Tieyong Zeng , Feng-Lei Fan

{"title":"Don’t fear peculiar activation functions: EUAF and beyond","authors":"Qianchao Wang , Shijun Zhang , Dong Zeng , Zhaoheng Xie , Hengtao Guo , Tieyong Zeng , Feng-Lei Fan","doi":"10.1016/j.neunet.2025.107258","DOIUrl":"10.1016/j.neunet.2025.107258","url":null,"abstract":"<div><div>In this paper, we propose a new super-expressive activation function called the Parametric Elementary Universal Activation Function (PEUAF). We demonstrate the effectiveness of PEUAF through systematic and comprehensive experiments on various industrial and image datasets, including CIFAR-10, Tiny-ImageNet, and ImageNet. The models utilizing PEUAF achieve the best performance across several baseline industrial datasets. Specifically, in image datasets, the models that incorporate mixed activation functions (with PEUAF) exhibit competitive test accuracy despite the low accuracy of models with only PEUAF. Moreover, we significantly generalize the family of super-expressive activation functions, whose existence has been demonstrated in several recent works by showing that any continuous function can be approximated to any desired accuracy by a fixed-size network with a specific super-expressive activation function. Specifically, our work addresses two major bottlenecks in impeding the development of super-expressive activation functions: the limited identification of super-expressive functions, which raises doubts about their broad applicability, and their often peculiar forms, which lead to skepticism regarding their scalability and practicality in real-world applications.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107258"},"PeriodicalIF":6.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471607","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

Spiking neural networks on FPGA: A survey of methodologies and recent advancements

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-14 DOI: 10.1016/j.neunet.2025.107256

Mehrzad Karamimanesh , Ebrahim Abiri , Mahyar Shahsavari , Kourosh Hassanli , André van Schaik , Jason Eshraghian

{"title":"Spiking neural networks on FPGA: A survey of methodologies and recent advancements","authors":"Mehrzad Karamimanesh , Ebrahim Abiri , Mahyar Shahsavari , Kourosh Hassanli , André van Schaik , Jason Eshraghian","doi":"10.1016/j.neunet.2025.107256","DOIUrl":"10.1016/j.neunet.2025.107256","url":null,"abstract":"<div><div>The mimicry of the biological brain’s structure in information processing enables spiking neural networks (SNNs) to exhibit significantly reduced power consumption compared to conventional systems. Consequently, these networks have garnered heightened attention and spurred extensive research endeavors in recent years, proposing various structures to achieve low power consumption, high speed, and improved recognition ability. However, researchers are still in the early stages of developing more efficient neural networks that more closely resemble the biological brain. This development and research require suitable hardware for execution with appropriate capabilities, and field-programmable gate array (FPGA) serves as a highly qualified candidate compared to existing hardware such as central processing unit (CPU) and graphics processing unit (GPU). FPGA, with parallel processing capabilities similar to the brain, lower latency and power consumption, and higher throughput, is highly eligible hardware for assisting in the development of spiking neural networks. In this review, an attempt has been made to facilitate researchers’ path to further develop this field by collecting and examining recent works and the challenges that hinder the implementation of these networks on FPGA.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107256"},"PeriodicalIF":6.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422441","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

Dual view graph transformer networks for multi-hop knowledge graph reasoning

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-14 DOI: 10.1016/j.neunet.2025.107260

Congcong Sun , Jianrui Chen , Zhongshi Shao , Junjie Huang

{"title":"Dual view graph transformer networks for multi-hop knowledge graph reasoning","authors":"Congcong Sun , Jianrui Chen , Zhongshi Shao , Junjie Huang","doi":"10.1016/j.neunet.2025.107260","DOIUrl":"10.1016/j.neunet.2025.107260","url":null,"abstract":"<div><div>To address the incompleteness of knowledge graphs, multi-hop reasoning aims to find the unknown information from existing data and enhance the comprehensive understanding. The presence of reasoning paths endows multi-hop reasoning with interpretability and traceability. Existing reinforcement learning (RL)-based multi-hop reasoning methods primarily rely on the agent’s blind trial-and-error approach in a large search space, which leads to inefficient training. In contrast, sequence-based multi-hop reasoning methods focus on learning the mapping from path to path to achieve better training efficiency, but they discard structured knowledge. The absence of structured knowledge directly hinders the ablity to capture and represent complex relations. To address the above issues, we propose a <strong>D</strong>ual <strong>V</strong>iew Graph Transformer Networks <strong>f</strong>or Multi-hop <strong>K</strong>nowledge <strong>G</strong>raph <strong>R</strong>easoning (DV4KGR), which enables the joint learning of structured and serialized views. The structured view contains a large amount of structured knowledge, which represents the relations among nodes from a global perspective. Meanwhile, the serialized view contains rich knowledge of reasoning semantics, aiding in training the mapping function from reasoning states to reasoning paths. We learn the representations of one-to-many relations in a supervised contrastive learning manner, which enhances the ability to represent complex relations. Additionally, we combine structured knowledge and rule induction for action smoothing, which effectively alleviates the overfitting problem associated with the end-to-end training mode. The experimental results on four benchmark datasets demonstrate that DV4KGR delivers better performance than the state-of-the-art baselines.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107260"},"PeriodicalIF":6.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429249","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

Heterogeneous boundary synchronization of time-delayed competitive neural networks with adaptive learning parameter in the space-time discretized frames

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-13 DOI: 10.1016/j.neunet.2025.107255

Tianwei Zhang , Shaobin Rao , Jianwen Zhou

引用次数: 0

Constraining an Unconstrained Multi-agent Policy with offline data

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-13 DOI: 10.1016/j.neunet.2025.107253

Cong Guan, Tao Jiang, Yi-Chen Li, Zongzhang Zhang, Lei Yuan, Yang Yu

{"title":"Constraining an Unconstrained Multi-agent Policy with offline data","authors":"Cong Guan, Tao Jiang, Yi-Chen Li, Zongzhang Zhang, Lei Yuan, Yang Yu","doi":"10.1016/j.neunet.2025.107253","DOIUrl":"10.1016/j.neunet.2025.107253","url":null,"abstract":"<div><div>Real-world multi-agent decision-making systems often have to satisfy some constraints, such as harmfulness, economics, etc., spurring the emergence of Constrained Multi-Agent Reinforcement Learning (CMARL). Existing studies of CMARL mainly focus on training a constrained policy in an online manner, that is, not only maximizing cumulative rewards but also not violating constraints. However, in practice, online learning may be infeasible due to safety restrictions or a lack of high-fidelity simulators. Moreover, as the learned policy runs, new constraints, that are not taken into account during training, may occur. To deal with the above two issues, we propose a method called <strong>C</strong>onstraining an <strong>U</strong>ncons<strong>T</strong>rained <strong>M</strong>ulti-<strong>A</strong>gent <strong>P</strong>olicy with offline data, dubbed <strong>CUTMAP</strong>, following the popular centralized training with decentralized execution paradigm. Specifically, we have formulated a scalable optimization objective within the framework of multi-agent maximum entropy reinforcement learning for CMARL. This approach is designed to estimate a decomposable Q-function by leveraging an unconstrained “prior policy”<span><span><sup>1</sup></span></span> in conjunction with cost signals extracted from offline data. When a new constraint comes, CUTMAP can reuse the prior policy without re-training it. To tackle the distribution shift challenge in offline learning, we also incorporate a conservative loss term when updating the Q-function. Therefore, the unconstrained prior policy can be trained to satisfy cost constraints through CUTMAP without the need for expensive interactions with the real environment, facilitating the practical application of MARL algorithms. Empirical results in several cooperative multi-agent benchmarks, including StarCraft games, particle games, food search games, and robot control, demonstrate the superior performance of our method.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107253"},"PeriodicalIF":6.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429229","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

Memristor-based circuit design of interweaving mechanism of emotional memory in a hippocamp-brain emotion learning model

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-13 DOI: 10.1016/j.neunet.2025.107276

Yunlai Zhu, Yongjie Zhao, Junjie Zhang, Xi Sun, Ying Zhu, Xu Zhou, Xuming Shen, Zuyu Xu, Zuheng Wu, Yuehua Dai

{"title":"Memristor-based circuit design of interweaving mechanism of emotional memory in a hippocamp-brain emotion learning model","authors":"Yunlai Zhu, Yongjie Zhao, Junjie Zhang, Xi Sun, Ying Zhu, Xu Zhou, Xuming Shen, Zuyu Xu, Zuheng Wu, Yuehua Dai","doi":"10.1016/j.neunet.2025.107276","DOIUrl":"10.1016/j.neunet.2025.107276","url":null,"abstract":"<div><div>Endowing robots with human-like emotional and cognitive abilities has garnered widespread attention, driving deep investigations into the complexities of these processes. However, few studies have examined the intricate circuits that govern the interplay between emotion and memory. This work presents a memristive circuit design that generates emotional memory, mimicking human emotional responses and memories while enabling interaction between emotions and cognition. Leveraging the hippocampal-brain emotion learning (BEL) architecture, the memristive circuit comprises seven comprehensive modules: the thalamus, sensory cortex, orbitofrontal cortex, amygdala, dentate gyrus (DG), CA3, and CA1. This design incorporates a compact biological framework, facilitating the collaborative encoding of emotional memories by the amygdala and hippocampus and allowing for flexible adjustment of circuit parameters to accommodate diverse personality traits. The proposed memristor-based circuit effectively mimics the complex interplay between emotions and memory, providing a valuable foundation for advancing the development of robots capable of replicating human-like emotional responses and cognitive integration.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107276"},"PeriodicalIF":6.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445534","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

Daydreaming Hopfield Networks and their surprising effectiveness on correlated data

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-13 DOI: 10.1016/j.neunet.2025.107216

Ludovica Serricchio , Dario Bocchi , Claudio Chilin , Raffaele Marino , Matteo Negri , Chiara Cammarota , Federico Ricci-Tersenghi

{"title":"Daydreaming Hopfield Networks and their surprising effectiveness on correlated data","authors":"Ludovica Serricchio , Dario Bocchi , Claudio Chilin , Raffaele Marino , Matteo Negri , Chiara Cammarota , Federico Ricci-Tersenghi","doi":"10.1016/j.neunet.2025.107216","DOIUrl":"10.1016/j.neunet.2025.107216","url":null,"abstract":"<div><div>To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that <em>perpetually</em> reinforces the patterns to be stored (as in the Hebb rule), and erases the spurious memories (as in dreaming algorithms). For this reason, we called it <em>Daydreaming</em>. Daydreaming is not destructive and it converges asymptotically to stationary retrieval maps. When trained on random uncorrelated examples, the model shows optimal performance in terms of the size of the basins of attraction of stored examples and the quality of reconstruction. We also train the Daydreaming algorithm on correlated data obtained via the random-features model and argue that it spontaneously exploits the correlations thus increasing even further the storage capacity and the size of the basins of attraction. Moreover, the Daydreaming algorithm is also able to stabilize the features hidden in the data. Finally, we test Daydreaming on the MNIST dataset and show that it still works surprisingly well, producing attractors that are close to unseen examples and class prototypes.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107216"},"PeriodicalIF":6.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Span-aware pre-trained network with deep information bottleneck for scientific entity relation extraction

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-11 DOI: 10.1016/j.neunet.2025.107250

Youwei Wang , Peisong Cao , Haichuan Fang , Yangdong Ye

{"title":"Span-aware pre-trained network with deep information bottleneck for scientific entity relation extraction","authors":"Youwei Wang , Peisong Cao , Haichuan Fang , Yangdong Ye","doi":"10.1016/j.neunet.2025.107250","DOIUrl":"10.1016/j.neunet.2025.107250","url":null,"abstract":"<div><div>Scientific entity relation extraction intends to promote the performance of each subtask through exploring the contextual representations with rich scientific semantics. However, most of existing models encounter the dilemma of scientific semantic dilution, where task-irrelevant information entangles with task-relevant information making science-friendly representation learning challenging. In addition, existing models isolate task-relevant information among subtasks, undermining the coherence of scientific semantics and consequently impairing the performance of each subtask. To deal with these challenges, a novel and effective <strong>S</strong>pan-aware <strong>P</strong>re-trained network with deep <strong>I</strong>nformation <strong>B</strong>ottleneck (SpIB) is proposed, which aims to conduct the scientific entity and relation extraction by minimizing task-irrelevant information and meanwhile maximizing the relatedness of task-relevant information. Specifically, SpIB model includes a minimum span-based representation learning (SRL) module and a relatedness-oriented task-relevant representation learning (TRL) module to disentangle the task-irrelevant information and discover the relatedness hidden in task-relevant information across subtasks. Then, an information minimum–maximum strategy is designed to minimize the mutual information of span-based representations and maximize the multivariate information of task-relevant representations. Finally, we design a unified loss function to simultaneously optimize the learned span-based and task-relevant representations. Experimental results on several scientific datasets, SciERC, ADE, BioRelEx, show the superiority of the proposed SpIB model over various the state-of-the-art models. The source code is publicly available at <span><span>https://github.com/SWT-AITeam/SpIB</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107250"},"PeriodicalIF":6.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422382","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

Hierarchical task network-enhanced multi-agent reinforcement learning: Toward efficient cooperative strategies

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-02-11 DOI: 10.1016/j.neunet.2025.107254

Xuechen Mu , Hankz Hankui Zhuo , Chen Chen , Kai Zhang , Chao Yu , Jianye Hao

{"title":"Hierarchical task network-enhanced multi-agent reinforcement learning: Toward efficient cooperative strategies","authors":"Xuechen Mu , Hankz Hankui Zhuo , Chen Chen , Kai Zhang , Chao Yu , Jianye Hao","doi":"10.1016/j.neunet.2025.107254","DOIUrl":"10.1016/j.neunet.2025.107254","url":null,"abstract":"<div><div>Navigating multi-agent reinforcement learning (MARL) environments with sparse rewards is notoriously difficult, particularly in suboptimal settings where exploration can be prematurely halted. To tackle these challenges, we introduce Hierarchical Symbolic Multi-Agent Reinforcement Learning (HS-MARL), a novel approach that incorporates hierarchical knowledge into MARL to effectively reduce the exploration space. We design intermediate states to decompose the state space into a hierarchical structure, represented using the Hierarchical Domain Definition Language (HDDL) and the option framework, forming domain knowledge and a symbolic option set. We leverage pyHIPOP+, an enhanced hierarchical task network (HTN) planner, to generate action sequences. A high-level meta-controller then assigns these symbolic options as policy functions, guiding low-level agents in their exploration of the environment. During this process, the meta-controller computes intrinsic rewards from the environmental rewards collected, which are used to train the symbolic option policies and refine pyHIPOP+’s heuristic function, thereby optimizing future action sequences. We evaluate HS-MARL with comparison to 15 state-of-the-art algorithms across two types of environments: four with sparse rewards and suboptimal conditions, and a real-world scenario involving a football match. Additionally, we perform an ablation study on HS-MARL’s intrinsic reward mechanism and pyHIPOP+, along with a sensitivity analysis of intrinsic reward hyperparameters. Our results show that HS-MARL significantly outperforms other methods in environments with sparse rewards and suboptimal conditions, underscoring the critical role of its intrinsic reward design and the pyHIPOP+ component. The code is available at: <span><span>https://github.com/Mxc666/HS-MARL.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107254"},"PeriodicalIF":6.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422383","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