A kind of 2-dimensional neural network model with delay is considered. By analyzing the distribution of the roots of the characteristic equation associated with the model, a bifurcation diagram was drawn in an appropr...A kind of 2-dimensional neural network model with delay is considered. By analyzing the distribution of the roots of the characteristic equation associated with the model, a bifurcation diagram was drawn in an appropriate parameter plane. It is found that a line is a pitchfork bifurcation curve. Further more, the stability of each fixed point and existence of Hopf bifurcation were obtained. Finally, the direction of the Hopf bifurcation and the stability of the bifurcating periodic solutions were determined by using the normal form method and centre manifold theory.展开更多
针对无线电信号的攻击愈来愈频繁的情况,本文在数据流形理论基础上,使用深度神经网络(DNN)检测无线电信号对抗样本及其攻击方法。首先使用5种不同攻击方法对无线电信号进行攻击产生对抗样本,其次使用3种不同的神经网络检测对抗样本,最...针对无线电信号的攻击愈来愈频繁的情况,本文在数据流形理论基础上,使用深度神经网络(DNN)检测无线电信号对抗样本及其攻击方法。首先使用5种不同攻击方法对无线电信号进行攻击产生对抗样本,其次使用3种不同的神经网络检测对抗样本,最后用残差神经网络(ResNet)检测对抗样本的攻击方法。在信噪比(SNR)为30 d B和20 dB的无线电信号数据上的实验结果表明,本文所使用的残差神经网络检测精度接近100%,在信噪比为10 dB的无线电信号数据上的检测精度仍然在90%以上。结果表明本文所用的残差神经网络能有效检测无线电信号的对抗样本及其攻击方法。展开更多
多标签学习已成功应用于文本分类、图像识别等各个领域。流行的技术包括提取标签特定特征、利用标签相关性等。提出带有标签相关性的预测调整算法PALC(Prediction adjusting with label correlation)将标签相关性融入串行并行神经网络...多标签学习已成功应用于文本分类、图像识别等各个领域。流行的技术包括提取标签特定特征、利用标签相关性等。提出带有标签相关性的预测调整算法PALC(Prediction adjusting with label correlation)将标签相关性融入串行并行神经网络。一方面,采用新颖的、更有效的串行并行神经网络架构来替代常见的显式特征提取或压缩感知方法;另一方面,考虑用固有的标签矩阵内的相关性来计算相关性矩阵,并以流形正则的方式优化分类器。对10个基准数据集与7种流行算法进行比较,结果表明PALC在3大排名指标下均有优势。展开更多
文摘A kind of 2-dimensional neural network model with delay is considered. By analyzing the distribution of the roots of the characteristic equation associated with the model, a bifurcation diagram was drawn in an appropriate parameter plane. It is found that a line is a pitchfork bifurcation curve. Further more, the stability of each fixed point and existence of Hopf bifurcation were obtained. Finally, the direction of the Hopf bifurcation and the stability of the bifurcating periodic solutions were determined by using the normal form method and centre manifold theory.
文摘针对无线电信号的攻击愈来愈频繁的情况,本文在数据流形理论基础上,使用深度神经网络(DNN)检测无线电信号对抗样本及其攻击方法。首先使用5种不同攻击方法对无线电信号进行攻击产生对抗样本,其次使用3种不同的神经网络检测对抗样本,最后用残差神经网络(ResNet)检测对抗样本的攻击方法。在信噪比(SNR)为30 d B和20 dB的无线电信号数据上的实验结果表明,本文所使用的残差神经网络检测精度接近100%,在信噪比为10 dB的无线电信号数据上的检测精度仍然在90%以上。结果表明本文所用的残差神经网络能有效检测无线电信号的对抗样本及其攻击方法。
文摘多标签学习已成功应用于文本分类、图像识别等各个领域。流行的技术包括提取标签特定特征、利用标签相关性等。提出带有标签相关性的预测调整算法PALC(Prediction adjusting with label correlation)将标签相关性融入串行并行神经网络。一方面,采用新颖的、更有效的串行并行神经网络架构来替代常见的显式特征提取或压缩感知方法;另一方面,考虑用固有的标签矩阵内的相关性来计算相关性矩阵,并以流形正则的方式优化分类器。对10个基准数据集与7种流行算法进行比较,结果表明PALC在3大排名指标下均有优势。