Neural Networks最新文献

英文中文

Weakly supervised label learning flows 弱监督标签学习流程

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-10 DOI: 10.1016/j.neunet.2024.106892

You Lu , Wenzhuo Song , Chidubem Arachie , Bert Huang

Supervised learning usually requires a large amount of labeled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some data. Many existing weakly supervised learning methods learn a deterministic function that estimates labels given the input data and weak signals. In this paper, we develop label learning flows (LLF), a general framework for weakly supervised learning problems. Our method is a generative model based on normalizing flows. The main idea of LLF is to optimize the conditional likelihoods of all possible labelings of the data within a constrained space defined by weak signals. We develop a training method for LLF that trains the conditional flow inversely and avoids estimating the labels. Once a model is trained, we can make predictions with a sampling algorithm. We apply LLF to three weakly supervised learning problems. Experiment results show that our method outperforms many baselines we compare against.

监督学习通常需要大量的标签数据。然而，对于许多任务来说，获得地面真实标签的成本很高。或者，弱监督方法利用廉价的弱信号进行学习，这些信号只能近似地标注一些数据。许多现有的弱监督学习方法都是在输入数据和弱信号的情况下，学习一个估计标签的确定性函数。在本文中，我们开发了标签学习流（LLF），这是一种用于弱监督学习问题的通用框架。我们的方法是一种基于归一化流的生成模型。LLF 的主要思想是在弱信号定义的受限空间内优化数据所有可能标签的条件似然性。我们为 LLF 开发了一种训练方法，可以反向训练条件流，避免估计标签。一旦模型训练完成，我们就可以使用采样算法进行预测。我们将 LLF 应用于三个弱监督学习问题。实验结果表明，我们的方法优于与之比较的许多基线方法。

引用次数: 0

Outer synchronization and outer H_∞ synchronization for coupled fractional-order reaction-diffusion neural networks with multiweights. 多权重耦合分数阶反应扩散神经网络的外同步和外 H∞ 同步

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-09 DOI: 10.1016/j.neunet.2024.106893

Jin-Liang Wang, Si-Yang Wang, Yan-Ran Zhu, Tingwen Huang

This paper introduces multiple state or spatial-diffusion coupled fractional-order reaction-diffusion neural networks, and discusses the outer synchronization and outer H_∞ synchronization problems for these coupled fractional-order reaction-diffusion neural networks (CFRNNs). The Lyapunov functional method, Laplace transform and inequality techniques are utilized to obtain some outer synchronization conditions for CFRNNs. Moreover, some criteria are also provided to make sure the outer H_∞ synchronization of CFRNNs. Finally, the derived outer and outer H_∞ synchronization conditions are validated on the basis of two numerical examples.

本文介绍了多态或空间扩散耦合分数阶反应扩散神经网络，并讨论了这些耦合分数阶反应扩散神经网络（CFRNN）的外同步和外H∞同步问题。利用李亚普诺夫函数法、拉普拉斯变换和不等式技术，得到了 CFRNN 的一些外同步条件。此外，还提供了一些标准来确保 CFRNN 的外同步 H∞。最后，基于两个数值示例验证了推导出的外同步和外 H∞ 同步条件。

引用次数: 0

Complexities of feature-based learning systems, with application to reservoir computing 基于特征的学习系统的复杂性，并将其应用于水库计算。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-09 DOI: 10.1016/j.neunet.2024.106883

Hiroki Yasumoto, Toshiyuki Tanaka

This paper studies complexity measures of reservoir systems. For this purpose, a more general model that we call a feature-based learning system, which is the composition of a feature map and of a final estimator, is studied. We study complexity measures such as growth function, VC-dimension, pseudo-dimension and Rademacher complexity. On the basis of the results, we discuss how the unadjustability of reservoirs and the linearity of readouts can affect complexity measures of the reservoir systems. Furthermore, some of the results generalize or improve the existing results.

本文研究水库系统的复杂性度量。为此，我们研究了一个更一般的模型，我们称之为基于特征的学习系统，它是特征图和最终估计器的组合。我们研究了增长函数、VC 维度、伪维度和拉德马赫复杂性等复杂性度量。在这些结果的基础上，我们讨论了水库的不可调整性和读数的线性如何影响水库系统的复杂度。此外，一些结果还概括或改进了现有结果。

引用次数: 0

TSOM: Small object motion detection neural network inspired by avian visual circuit TSOM：受鸟类视觉回路启发的小物体运动检测神经网络。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-09 DOI: 10.1016/j.neunet.2024.106881

Pingge Hu , Xiaoteng Zhang , Mengmeng Li , Yingjie Zhu , Li Shi

Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and the Retina-OT-Rt visual circuit of birds is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical description based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The TSOM neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each corresponding to neurons in the visual pathway for precise topographic projection, spatial–temporal encoding, motion feature selection, and multi-directional motion integration. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.

对于机器视觉系统来说，从高空视角检测复杂背景中的小型移动物体是一项极具挑战性的任务。鸟类视觉系统从大自然中获得灵感，能够处理各种复杂空中场景中的运动信息，而且鸟类的视网膜-OT-Rt 视觉回路对从高空捕捉小物体的运动信息非常敏感。然而，基于鸟类视觉系统的小物体运动检测算法还有待进一步研究。在本文中，我们在广泛研究视网膜-OT-Rt 视觉回路生物机制的基础上进行了数学描述。在此基础上，我们提出了一种新型的视网膜小物体运动检测神经网络（TSOM）。TSOM神经网络包括视网膜层、SGC树突层、SGC索玛层和Rt层，分别对应视觉通路中的神经元，用于精确的地形投射、时空编码、运动特征选择和多向运动整合。在鸽子神经生理学实验和图像序列数据上进行的大量实验表明，TSOM 具有生物可解释性，能有效地从复杂的高空背景中提取可靠的小物体运动特征。

{"title":"TSOM: Small object motion detection neural network inspired by avian visual circuit","authors":"Pingge Hu , Xiaoteng Zhang , Mengmeng Li , Yingjie Zhu , Li Shi","doi":"10.1016/j.neunet.2024.106881","DOIUrl":"10.1016/j.neunet.2024.106881","url":null,"abstract":"<div><div>Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and the Retina-OT-Rt visual circuit of birds is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical description based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The TSOM neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each corresponding to neurons in the visual pathway for precise topographic projection, spatial–temporal encoding, motion feature selection, and multi-directional motion integration. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"182 ","pages":"Article 106881"},"PeriodicalIF":6.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645085","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

Evolutionary architecture search for generative adversarial networks using an aging mechanism-based strategy 使用基于老化机制的策略为生成式对抗网络寻找进化架构

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-09 DOI: 10.1016/j.neunet.2024.106877

Wenxing Man, Liming Xu, Chunlin He

Generative Adversarial Networks (GANs) have emerged as a key technology in artificial intelligence, especially in image generation. However, traditionally hand-designed GAN architectures often face significant training stability challenges, which are effectively addressed by our Evolutionary Neural Architecture Search (ENAS) algorithm for GANs, named EAMGAN. This one-shot model automates the design of GAN architectures and employs an Operation Importance Metric (OIM) to enhance training stability. It also incorporates an aging mechanism to optimize the selection process during architecture search. Additionally, the use of a non-dominated sorting algorithm ensures the generation of Pareto-optimal solutions, promoting diversity and preventing premature convergence. We evaluated our method on benchmark datasets, and the results demonstrate that EAMGAN is highly competitive in terms of efficiency and performance. Our method identified an architecture achieving Inception Scores (IS) of 8.83±0.13 and Fréchet Inception Distance (FID) of 9.55 on CIFAR-10 with only 0.66 GPU days. Results on the STL-10, CIFAR-100, and ImageNet32 datasets further demonstrate the robust portability of our architecture.

生成对抗网络（GAN）已成为人工智能领域的一项关键技术，尤其是在图像生成方面。然而，传统手工设计的 GAN 架构往往面临训练稳定性方面的巨大挑战，而我们的 GAN 演化神经架构搜索（ENAS）算法（名为 EAMGAN）则有效地解决了这一问题。这种一次性模型可自动设计 GAN 架构，并采用操作重要性度量（OIM）来提高训练稳定性。它还采用了一种老化机制，以优化架构搜索过程中的选择过程。此外，非主导排序算法的使用确保了帕累托最优解的生成，促进了多样性并防止了过早收敛。我们在基准数据集上对我们的方法进行了评估，结果表明 EAMGAN 在效率和性能方面具有很强的竞争力。我们的方法确定了一种架构，在 CIFAR-10 上实现了 8.83±0.13 的入门分数（IS）和 9.55 的弗雷谢特入门距离（FID），而 GPU 日数仅为 0.66 天。在 STL-10、CIFAR-100 和 ImageNet32 数据集上的结果进一步证明了我们的架构具有强大的可移植性。

{"title":"Evolutionary architecture search for generative adversarial networks using an aging mechanism-based strategy","authors":"Wenxing Man, Liming Xu, Chunlin He","doi":"10.1016/j.neunet.2024.106877","DOIUrl":"10.1016/j.neunet.2024.106877","url":null,"abstract":"<div><div>Generative Adversarial Networks (GANs) have emerged as a key technology in artificial intelligence, especially in image generation. However, traditionally hand-designed GAN architectures often face significant training stability challenges, which are effectively addressed by our Evolutionary Neural Architecture Search (ENAS) algorithm for GANs, named EAMGAN. This one-shot model automates the design of GAN architectures and employs an Operation Importance Metric (OIM) to enhance training stability. It also incorporates an aging mechanism to optimize the selection process during architecture search. Additionally, the use of a non-dominated sorting algorithm ensures the generation of Pareto-optimal solutions, promoting diversity and preventing premature convergence. We evaluated our method on benchmark datasets, and the results demonstrate that EAMGAN is highly competitive in terms of efficiency and performance. Our method identified an architecture achieving Inception Scores (IS) of 8.83±0.13 and Fréchet Inception Distance (FID) of 9.55 on CIFAR-10 with only 0.66 GPU days. Results on the STL-10, CIFAR-100, and ImageNet32 datasets further demonstrate the robust portability of our architecture.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106877"},"PeriodicalIF":6.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631295","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

A bio-inspired visual collision detection network integrated with dynamic temporal variance feedback regulated by scalable functional countering jitter streaming 由生物启发的视觉碰撞检测网络，集成了由可扩展功能性反抖动流调节的动态时差反馈。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-08 DOI: 10.1016/j.neunet.2024.106882

Zefang Chang , Hao Chen , Mu Hua , Qinbing Fu , Jigen Peng

In pursuing artificial intelligence for efficient collision avoidance in robots, researchers draw inspiration from the locust’s visual looming-sensitive neural circuit to establish an efficient neural network for collision detection. However, existing bio-inspired collision detection neural networks encounter challenges posed by jitter streaming, a phenomenon commonly experienced, for example, when a ground robot moves across uneven terrain. Visual inputs from jitter streaming induce significant fluctuations in grey values, distracting existing bio-inspired networks from extracting visually looming features. To overcome this limitation, we derive inspiration from the potential of feedback loops to enable the brain to generate a coherent visual perception. We introduce a novel dynamic temporal variance feedback loop regulated by scalable functional into the traditional bio-inspired collision detection neural network. This feedback mechanism extracts dynamic temporal variance information from the output of higher-order neurons in the conventional network to assess the fluctuation level of local neural responses and regulate it by a scalable functional to differentiate variance induced by incoherent visual input. Then the regulated signal is reintegrated into the input through negative feedback loop to reduce the incoherence of the signal within the network. Numerical experiments substantiate the effectiveness of the proposed feedback loop in promoting collision detection against jitter streaming. This study extends the capabilities of bio-inspired collision detection neural networks to address jitter streaming challenges, offering a novel insight into the potential of feedback mechanisms in enhancing visual neural abilities.

在研究人工智能如何帮助机器人高效避免碰撞的过程中，研究人员从蝗虫的视觉隐现敏感神经回路中汲取灵感，建立了一种高效的碰撞检测神经网络。然而，现有的生物启发碰撞检测神经网络遇到了抖动流带来的挑战，例如，当地面机器人在不平坦的地形上移动时，通常会遇到抖动流现象。来自抖动流的视觉输入会引起灰度值的显著波动，从而干扰现有的生物启发网络提取视觉隐约特征。为了克服这一局限，我们从反馈回路的潜力中获得灵感，使大脑产生连贯的视觉感知。我们在传统的生物启发碰撞检测神经网络中引入了由可扩展功能调节的新型动态时差反馈回路。这种反馈机制从传统网络中高阶神经元的输出中提取动态时间方差信息，以评估局部神经反应的波动水平，并通过可扩展函数对其进行调节，以区分不连贯视觉输入引起的方差。然后，调节后的信号通过负反馈回路重新整合到输入中，以减少网络内信号的不连贯。数值实验证实了所提出的反馈回路在促进碰撞检测以对抗抖动流方面的有效性。这项研究扩展了生物启发碰撞检测神经网络的能力，以应对抖动流的挑战，为反馈机制在增强视觉神经能力方面的潜力提供了新的见解。

{"title":"A bio-inspired visual collision detection network integrated with dynamic temporal variance feedback regulated by scalable functional countering jitter streaming","authors":"Zefang Chang , Hao Chen , Mu Hua , Qinbing Fu , Jigen Peng","doi":"10.1016/j.neunet.2024.106882","DOIUrl":"10.1016/j.neunet.2024.106882","url":null,"abstract":"<div><div>In pursuing artificial intelligence for efficient collision avoidance in robots, researchers draw inspiration from the locust’s visual looming-sensitive neural circuit to establish an efficient neural network for collision detection. However, existing bio-inspired collision detection neural networks encounter challenges posed by jitter streaming, a phenomenon commonly experienced, for example, when a ground robot moves across uneven terrain. Visual inputs from jitter streaming induce significant fluctuations in grey values, distracting existing bio-inspired networks from extracting visually looming features. To overcome this limitation, we derive inspiration from the potential of feedback loops to enable the brain to generate a coherent visual perception. We introduce a novel dynamic temporal variance feedback loop regulated by scalable functional into the traditional bio-inspired collision detection neural network. This feedback mechanism extracts dynamic temporal variance information from the output of higher-order neurons in the conventional network to assess the fluctuation level of local neural responses and regulate it by a scalable functional to differentiate variance induced by incoherent visual input. Then the regulated signal is reintegrated into the input through negative feedback loop to reduce the incoherence of the signal within the network. Numerical experiments substantiate the effectiveness of the proposed feedback loop in promoting collision detection against jitter streaming. This study extends the capabilities of bio-inspired collision detection neural networks to address jitter streaming challenges, offering a novel insight into the potential of feedback mechanisms in enhancing visual neural abilities.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"182 ","pages":"Article 106882"},"PeriodicalIF":6.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645079","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

Dopamine-induced relaxation of spike synchrony diversifies burst patterns in cultured hippocampal networks 多巴胺诱导的尖峰同步松弛使培养海马网络中的突发性模式多样化

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-07 DOI: 10.1016/j.neunet.2024.106888

Huu Hoang , Nobuyoshi Matsumoto , Miyuki Miyano , Yuji Ikegaya , Aurelio Cortese

The intricate interplay of neurotransmitters orchestrates a symphony of neural activity in the hippocampus, with dopamine emerging as a key conductor in this complex ensemble. Despite numerous studies uncovering the cellular mechanisms of dopamine, its influence on hippocampal neural networks remains elusive. Combining in vitro electrophysiological recordings of rat embryonic hippocampal neurons, pharmacological interventions, and computational analyses of spike trains, we found that dopamine induces a relaxation in network synchrony. This relaxation expands the repertoire of burst dynamics within these hippocampal networks, a phenomenon notably absent under the administration of dopamine antagonists. Our study provides a thorough understanding of how dopamine signaling influences the formation of functional networks among hippocampal neurons.

神经递质之间错综复杂的相互作用为海马体的神经活动谱写了一曲交响乐，而多巴胺则是这一复杂合奏中的关键指挥。尽管有大量研究揭示了多巴胺的细胞机制，但它对海马神经网络的影响仍然难以捉摸。结合对大鼠胚胎海马神经元的体外电生理记录、药理学干预以及对尖峰列车的计算分析，我们发现多巴胺会诱导网络同步性的松弛。这种松弛扩大了这些海马网络中突发性动态的范围，而这种现象在服用多巴胺拮抗剂后明显消失。我们的研究让我们对多巴胺信号如何影响海马神经元间功能网络的形成有了一个全面的了解。

引用次数: 0

Barrier-critic-disturbance approximate optimal control of nonzero-sum differential games for modular robot manipulators 模块化机器人操纵器的非零和微分博弈的障碍批判-扰动近似最优控制。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-06 DOI: 10.1016/j.neunet.2024.106880

Bo Dong, Xinye Zhu, Tianjiao An, Hucheng Jiang, Bing Ma

In this paper, for addressing the safe control problem of modular robot manipulators (MRMs) system with uncertain disturbances, an approximate optimal control scheme of nonzero-sum (NZS) differential games is proposed based on the control barrier function (CBF). The dynamic model of the manipulator system integrates joint subsystems through the utilization of joint torque feedback (JTF) technique, incorporating interconnected dynamic coupling (IDC) effects. By integrating the cost functions relevant to each player with the CBF, the evolution of system states is ensured to remain within the safe region. Subsequently, the optimal tracking control problem for the MRM system is reformulated as an NZS game involving multiple joint subsystems. Based on the adaptive dynamic programming (ADP) algorithm, a cost function approximator for solving Hamilton–Jacobi (HJ) equation using only critic neural networks (NN) is established, which promotes the feasible derivation of the approximate optimal control strategy. The Lyapunov theory is utilized to demonstrate that the tracking error is uniformly ultimately bounded (UUB). Utilizing the CBF’s state constraint mechanism prevents the robot from deviating from the safe region, and the application of the NZS game approach ensures that the subsystems of the MRM reach a Nash equilibrium. The proposed control method effectively addresses the problem of safe and approximate optimal control of MRM system under uncertain disturbances. Finally, the effectiveness and superiority of the proposed method are verified through simulations and experiments.

本文针对具有不确定干扰的模块化机器人机械手（MRMs）系统的安全控制问题，提出了一种基于控制障碍函数（CBF）的非零和（NZS）微分博弈近似最优控制方案。操纵器系统的动态模型通过利用关节扭矩反馈（JTF）技术，结合互连动态耦合（IDC）效应，集成了关节子系统。通过将与每个参与者相关的成本函数与 CBF 相结合，可确保系统状态的演变保持在安全区域内。随后，MRM 系统的最优跟踪控制问题被重新表述为涉及多个联合子系统的 NZS 博弈。基于自适应动态编程（ADP）算法，建立了仅使用批判神经网络（NN）求解汉密尔顿-雅可比（HJ）方程的代价函数近似器，从而促进了近似最优控制策略的可行推导。利用 Lyapunov 理论证明了跟踪误差是均匀最终有界的（UUB）。利用 CBF 的状态约束机制可防止机器人偏离安全区域，而 NZS 博弈方法的应用可确保 MRM 子系统达到纳什均衡。所提出的控制方法有效地解决了不确定干扰下 MRM 系统的安全近似最优控制问题。最后，通过仿真和实验验证了所提方法的有效性和优越性。

{"title":"Barrier-critic-disturbance approximate optimal control of nonzero-sum differential games for modular robot manipulators","authors":"Bo Dong, Xinye Zhu, Tianjiao An, Hucheng Jiang, Bing Ma","doi":"10.1016/j.neunet.2024.106880","DOIUrl":"10.1016/j.neunet.2024.106880","url":null,"abstract":"<div><div>In this paper, for addressing the safe control problem of modular robot manipulators (MRMs) system with uncertain disturbances, an approximate optimal control scheme of nonzero-sum (NZS) differential games is proposed based on the control barrier function (CBF). The dynamic model of the manipulator system integrates joint subsystems through the utilization of joint torque feedback (JTF) technique, incorporating interconnected dynamic coupling (IDC) effects. By integrating the cost functions relevant to each player with the CBF, the evolution of system states is ensured to remain within the safe region. Subsequently, the optimal tracking control problem for the MRM system is reformulated as an NZS game involving multiple joint subsystems. Based on the adaptive dynamic programming (ADP) algorithm, a cost function approximator for solving Hamilton–Jacobi (HJ) equation using only critic neural networks (NN) is established, which promotes the feasible derivation of the approximate optimal control strategy. The Lyapunov theory is utilized to demonstrate that the tracking error is uniformly ultimately bounded (UUB). Utilizing the CBF’s state constraint mechanism prevents the robot from deviating from the safe region, and the application of the NZS game approach ensures that the subsystems of the MRM reach a Nash equilibrium. The proposed control method effectively addresses the problem of safe and approximate optimal control of MRM system under uncertain disturbances. Finally, the effectiveness and superiority of the proposed method are verified through simulations and experiments.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106880"},"PeriodicalIF":6.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142639976","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

Rigid propagation of visual motion in the insect’s neural system 视觉运动在昆虫神经系统中的刚性传播

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-06 DOI: 10.1016/j.neunet.2024.106874

Hao Chen , Boquan Fan , Haiyang Li , Jigen Peng

In the pursuit of developing an efficient artificial visual system for visual motion detection, researchers find inspiration from the visual motion-sensitive neural pathways in the insect’s neural system. Although multiple proposed neural computational models exhibit significant performance aligned with those observed from insects, the mathematical basis for how these models characterize the sensitivity of visual neurons to corresponding motion patterns remains to be elucidated. To fill this research gap, this study originally proposed that the rigid propagation of visual motion is an essential mathematical property of the models for the insect’s visual neural system, meaning that the dynamics of the model output remain consistent with the visual motion dynamics reflected in the input. To verify this property, this study uses the small target motion detector (STMD) neural pathway — one of the visual motion-sensitive pathways in the insect’s neural system — as an exemplar, rigorously demonstrating that the dynamics of translational visual motion are rigidly propagated through the encoding of retinal measurements in STMD computational models. Numerical experiment results further substantiate the proposed property of STMD models. This study offers a novel theoretical framework for exploring the nature of the visual motion perception underlying the insect’s visual neural system and brings an innovative perspective to the broader research field of insect visual motion perception and artificial visual systems.

为了开发用于视觉运动检测的高效人工视觉系统，研究人员从昆虫神经系统中对视觉运动敏感的神经通路中找到了灵感。尽管多个已提出的神经计算模型表现出了与昆虫观察到的模型一致的显著性能，但这些模型如何描述视觉神经元对相应运动模式的敏感性的数学基础仍有待阐明。为了填补这一研究空白，本研究最初提出视觉运动的刚性传播是昆虫视觉神经系统模型的基本数学特性，这意味着模型输出的动态与输入所反映的视觉运动动态保持一致。为了验证这一特性，本研究以昆虫神经系统中对视觉运动敏感的通路之一--小目标运动探测器（STMD）神经通路为例，严格证明了平移视觉运动的动态是通过STMD计算模型中的视网膜测量编码刚性传播的。数值实验结果进一步证实了所提出的 STMD 模型特性。这项研究为探索昆虫视觉神经系统底层视觉运动感知的本质提供了一个新颖的理论框架，并为昆虫视觉运动感知和人工视觉系统这一更广泛的研究领域带来了一个创新的视角。

{"title":"Rigid propagation of visual motion in the insect’s neural system","authors":"Hao Chen , Boquan Fan , Haiyang Li , Jigen Peng","doi":"10.1016/j.neunet.2024.106874","DOIUrl":"10.1016/j.neunet.2024.106874","url":null,"abstract":"<div><div>In the pursuit of developing an efficient artificial visual system for visual motion detection, researchers find inspiration from the visual motion-sensitive neural pathways in the insect’s neural system. Although multiple proposed neural computational models exhibit significant performance aligned with those observed from insects, the mathematical basis for how these models characterize the sensitivity of visual neurons to corresponding motion patterns remains to be elucidated. To fill this research gap, this study originally proposed that the rigid propagation of visual motion is an essential mathematical property of the models for the insect’s visual neural system, meaning that the dynamics of the model output remain consistent with the visual motion dynamics reflected in the input. To verify this property, this study uses the small target motion detector (STMD) neural pathway — one of the visual motion-sensitive pathways in the insect’s neural system — as an exemplar, rigorously demonstrating that the dynamics of translational visual motion are rigidly propagated through the encoding of retinal measurements in STMD computational models. Numerical experiment results further substantiate the proposed property of STMD models. This study offers a novel theoretical framework for exploring the nature of the visual motion perception underlying the insect’s visual neural system and brings an innovative perspective to the broader research field of insect visual motion perception and artificial visual systems.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106874"},"PeriodicalIF":6.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631415","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

AmbiBias Contrast: Enhancing debiasing networks via disentangled space from ambiguity-bias clusters AmbiBias 对比：通过来自模糊偏置群组的分离空间来增强去噪网络。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks

Pub Date : 2024-11-05 DOI: 10.1016/j.neunet.2024.106857

Suneung Kim, Seong-Whan Lee

The goal of debiasing in classification tasks is to train models to be less sensitive to correlations between a sample’s target attribution and periodically occurring contextual attributes to achieve accurate classification. A prevalent method involves applying re-weighing techniques to lower the weight of bias-aligned samples that contribute to bias, thereby focusing the training on bias-conflicting samples that deviate from the bias patterns. Our empirical analysis indicates that this approach is effective in datasets where bias-conflicting samples constitute a minority compared to bias-aligned samples, yet its effectiveness diminishes in datasets with similar proportions of both. This ineffectiveness in varied dataset compositions suggests that the traditional method cannot be practical in diverse environments as it overlooks the dynamic nature of dataset-induced biases. To address this issue, we introduce a contrastive approach named “AmbiBias Contrast”, which is robust across various dataset compositions. This method accounts for “ambiguity bias”— the variable nature of bias elements across datasets, which cannot be clearly defined. Given the challenge of defining bias due to the fluctuating compositions of datasets, we designed a method of representation learning that accommodates this ambiguity. Our experiments across a range of and dataset configurations verify the robustness of our method, delivering state-of-the-art performance.

在分类任务中，去偏差的目的是训练模型，使其对样本的目标属性与周期性出现的上下文属性之间的相关性不那么敏感，从而实现准确分类。一种流行的方法是应用重新加权技术来降低造成偏差的偏差对齐样本的权重，从而将训练重点放在偏离偏差模式的偏差冲突样本上。我们的实证分析表明，与偏差对齐样本相比，在偏差冲突样本占少数的数据集中，这种方法是有效的，但在两者比例相近的数据集中，这种方法的有效性就会降低。这种在不同数据集组成中的无效性表明，传统方法忽视了数据集引起的偏差的动态性质，因此在不同环境中无法实用。为了解决这个问题，我们引入了一种名为 "AmbiBias 对比 "的对比方法，这种方法在不同的数据集组成中都能保持稳定。这种方法考虑到了 "模糊偏差"--不同数据集的偏差元素性质各异，无法明确定义。鉴于数据集组成的波动性给偏差定义带来的挑战，我们设计了一种表征学习方法，以适应这种模糊性。我们在一系列数据集配置中进行的实验验证了我们方法的稳健性，并提供了最先进的性能。

{"title":"AmbiBias Contrast: Enhancing debiasing networks via disentangled space from ambiguity-bias clusters","authors":"Suneung Kim, Seong-Whan Lee","doi":"10.1016/j.neunet.2024.106857","DOIUrl":"10.1016/j.neunet.2024.106857","url":null,"abstract":"<div><div>The goal of debiasing in classification tasks is to train models to be less sensitive to correlations between a sample’s target attribution and periodically occurring contextual attributes to achieve accurate classification. A prevalent method involves applying re-weighing techniques to lower the weight of bias-aligned samples that contribute to bias, thereby focusing the training on bias-conflicting samples that deviate from the bias patterns. Our empirical analysis indicates that this approach is effective in datasets where bias-conflicting samples constitute a minority compared to bias-aligned samples, yet its effectiveness diminishes in datasets with similar proportions of both. This ineffectiveness in varied dataset compositions suggests that the traditional method cannot be practical in diverse environments as it overlooks the dynamic nature of dataset-induced biases. To address this issue, we introduce a contrastive approach named “AmbiBias Contrast”, which is robust across various dataset compositions. This method accounts for “ambiguity bias”— the variable nature of bias elements across datasets, which cannot be clearly defined. Given the challenge of defining bias due to the fluctuating compositions of datasets, we designed a method of representation learning that accommodates this ambiguity. Our experiments across a range of and dataset configurations verify the robustness of our method, delivering state-of-the-art performance.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"Article 106857"},"PeriodicalIF":6.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631292","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Neural Networks

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀