Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

Search research articles

相关实验视频

Updated: Jan 14, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

一个完整增强的适应梯度神经网络,用于kWTA和多机器人协调.

Haoen Huang, Wei He, Zhigang Zeng

IEEE transactions on cybernetics

|January 12, 2026

概括

此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Sliding Integral Neural Network Driven Robust Solution for Time-Varying Quadratic Programming.

IEEE transactions on neural networks and learning systems·2026

Same author

An Accelerated Augmented Gradient Neural Network for Constrained Time-Varying Nonlinear Optimization.

IEEE transactions on neural networks and learning systems·2026

Same author

A memristive fuzzy neural network with applications to classification task: A programmable circuit system.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Pseudomonas-Enterobacter Co-Infection Drives Cellulitis and Lymphangitis in Equines: A Case Report.

Veterinary sciences·2025

Same author

A Trust-Region Projection Neural Network for Nonlinear Programming.

IEEE transactions on neural networks and learning systems·2025

Same author

An Accelerated Approach on Adaptive Gradient Neural Network for Solving Time-Dependent Linear Equations: A State-Triggered Perspective.

IEEE transactions on neural networks and learning systems·2024

我们引入了一个完整增强的自适应梯度神经网络 (IAGNN),以改善k-winners-take-all (kWTA) 操作. 这种新的方法提高了稳定性,并减少了计算任务中的滞后错误.

科学领域:

计算神经科学是一种神经科学.
人工智能的人工智能
机器人技术机器人技术机器人技术

背景情况:

现有的k-winners-take-all (kWTA) 方法面临的挑战是滞后的错误,高复杂性和低稳定性.
这些局限性阻碍了高效的计算处理和现实世界的应用.

研究的目的:

为KWTA运算开发一种新的计算方法,克服现有的局限性.
引入完整增强的自适应梯度神经网络 (IAGNN),以提高kWTA的性能.

主要方法:

提出了综合增强的自适应梯度神经网络 (IAGNN).
整合一个适应系数以减轻滞后错误.
从理论上分析利亚普诺夫的稳定性和强度.
进行数值模拟以进行验证.

主要成果:

IAGNN有效地消除了滞后错误,同时保持了O ((n^2) 复杂度.
利亚普诺夫的稳定性和IAGNN的强度被数学证明了.
数字模拟证实了模型的稳定性和强度.
在多机器人追踪系统中的实施证明了操作可行性和耐噪声.

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jan 14, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

结论:

IAGNN为kWTA运行提供了重大进步,解决了以前方法的关键局限性.
IAGNN在复杂的系统中显示了实际的可行性和弹性,例如多机器人协调.