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

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

Speech Recognition with an fMRISNN Constrained by Human Functional Brain Networks: A Study of Enhanced MFCC-Driven Sparse Spike Encoding.

Biomimetics (Basel, Switzerland)·2026

Same author

Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack.

Biomimetics (Basel, Switzerland)·2025

Same author

Specific Neural Coding of Complex Neural Network Based on Time Coding Under Various Exterior Stimuli.

Biomimetics (Basel, Switzerland)·2025

Same author

Anti-Disturbance of Scale-Free Spiking Neural Network against Impulse Noise.

Brain sciences·2023

Same author

Does the Low-Carbon City Pilot Policy Improve the Urban Land Green Use Efficiency?-Investigation Based on Multi-Period Difference-in-Differences Model.

International journal of environmental research and public health·2023

Same author

Complex spiking neural networks with synaptic time-delay based on anti-interference function.

Cognitive neurodynamics·2022

Search research articles

相关实验视频

Updated: May 25, 2025

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

复杂的尖端神经网络通过在随机攻击下受伤抵抗来评估.

Lei Guo^1,2, Chongming Li^1,2, Huan Liu^1,2

¹Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, China.

|February 26, 2025

概括

这项研究介绍了复杂的尖端神经网络 (Com-SNN),这是一个生物可信的脑启发模型,可以增强伤害抵抗力. 与其他模型相比,Com-SNN表现出优越的弹性,突出突出突触可塑性和网络拓学的重要性.

关键词:

大脑启发的模型复杂的网络拓结构.伤害抵抗力伤害抵抗力伤害抵抗力伤害抵抗机制的机制尖的神经网络的神经网络.突触性可塑性突触性可塑性

更多相关视频

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Published on: January 20, 2023

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

相关实验视频

Last Updated: May 25, 2025

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

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Published on: January 20, 2023

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

科学领域:

人工智能的人工智能
计算神经科学是一种神经科学.
网络科学网络科学

背景情况:

大脑启发的模型对人工智能至关重要,但与环境复杂性作斗争,缺乏生物可信性.
提高人工神经网络的伤害抵抗力对于强大的AI系统至关重要.
人类大脑在受伤时表现出自我适应能力,为弹性AI提供蓝图.

研究的目的:

提出一种由大脑启发的新型模型,复杂的尖端神经网络 (Com-SNN),具有增强的生物可信性和抗损伤能力.
研究Com-SNN内部的伤害抵抗机制,重点关注突触可塑性和网络拓.
在模拟攻击下,比较Com-SNN对替代尖端神经网络 (SNN) 的伤害抵抗力.

主要方法:

开发了Com-SNN模型,其拓受到生物大脑网络的启发,利用Izhikevich神经元模型和时间延迟的突触可塑性.
使用两个指标评估了Com-SNN受伤阻力,并将其与模拟神经元去除 (随机攻击) 下的其他SNN进行了比较.
在随机攻击期间分析了Com-SNN的突触可塑性动态和拓特征,以了解弹性机制.

主要成果:

与具有替代拓的SNN相比,Com-SNN表现出明显优越的伤害抵抗力.
实验结果证实了拟议模型在提高尖端神经网络的整体伤害抵抗能力方面的潜力.
该研究成功地证明了Com-SNN在模拟物理攻击下增强的弹性.

结论:

突触可塑性被确定为一个基本因素,有助于大脑灵感模型的伤害抵抗.
网络拓在确定尖端神经网络的弹性和强度方面发挥着至关重要的作用.
这些发现为开发更强大,生物可信的人工智能系统提供了洞察力.