相关实验视频

Updated: Sep 10, 2025

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

通过视网膜类编码和基于记忆的神经元,提高尖端神经网络的稳定性

Jiahong Zhang¹, Kexin Wang¹, Man Yao²

¹Institute of Automation, Chinese Academy of Sciences, Beijing, 100045, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China.

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

|August 19, 2025

概括

尖端神经网络 (SNN) 使用新型视网膜样编码和基于记忆的尖端神经元 (MSN) 显示了对图像损坏的强大改进. 这提高了SNN在CIFAR10-C和ImageNet-C等受损数据集上的性能.

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.
计算机视觉计算机视觉

背景情况:

尖端神经网络 (SNN) 与传统的人工神经网络 (ANN) 相比,提供了能源效率和生物可信性.
当前的SNN面临着在现实应用中对损坏的图像保持稳健性的挑战.
现有的SNN需要强大的基准来评估在图像腐败下的性能.

研究的目的:

使用已建立的ANN腐败数据集 (CIFAR10-C,ImageNet-C) 评估SNN的稳定性.
开发新的方法来增强SNN对图像腐败的强度.
提高SNNs在复杂的视觉环境中的实际应用性.

主要方法:

引入CIFAR10-C和ImageNet-C数据集用于SNN稳定性基准测试.
关于类似视网膜的编码策略的建议,以模仿动态的人类视觉感知.
基于记忆的尖端神经元 (MSN) 和其平行变体 (MPSN) 的开发,用于强大的特征学习.

主要成果:

提出的方法显著提高了SNN识别对受损数据集的准确性和稳定性.
在CIFAR10-C上达到87.04%的准确性,在ImageNet-C上达到40.37%,超过了最先进的SNN.
与现有的SNN方法相比,在损坏的图像基准上表现出卓越的性能.

结论:

新的视网膜样编码和MSN/MPSN显著提高了SNN对图像损坏的稳定性.
开发的方法提供了一个可行的解决方案,用于在现实世界中部署SNNs的情景与不完美的数据.
这项工作为计算机视觉中更具弹性和可解释性的SNNs铺平了道路.

关键词:

腐败的强度腐败的强度图像识别图像识别图像识别基于记忆的尖端神经元.尖的神经元网络是指神经元网络.

更多相关视频

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus

Inducing Long-Term Plasticity of Intrinsic Neuronal Excitability in Neurons of the Dorsal Lateral Geniculate Nucleus

Published on: September 20, 2024

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

相关概念视频

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

The Retina

The Retina

The retina is a layer of nervous tissue at the back of the eye that transduces light into neural signals. This process, called phototransduction, is carried out by rod and cone photoreceptor cells in the back of the retina.