By applying phase-only technique in array antenna pattern synthesis, antenna arrays can form desired patterns with the use of phase shifters only. A novel phase-only pattern synthesis algorithm is proposed for the pas...By applying phase-only technique in array antenna pattern synthesis, antenna arrays can form desired patterns with the use of phase shifters only. A novel phase-only pattern synthesis algorithm is proposed for the passive phased array seeker. This algorithm synthesizes the main beam of the antenna pattern through least-squares approximation, thus minimizing the errors between the actual and the desired main beams. The synthesis problem can be solved by applying gradient-descent optimization. The item for suppressing side lobes is added to the above synthesis problem. To obtain a side lobe level as low as possible, the algorithm assigns different weights to different directions in the side lobe region. The algorithm is run repeatedly and the weights are adjusted adaptively according to the normalized power in the side lobe directions. Detailed examples are presented to demonstrate the accuracy and effectiveness of the proposed approach.展开更多
差分隐私被广泛应用于联邦学习中,以保障模型参数的安全,但不够合理的加噪方式会限制模型准确度进一步提高。为此,提出一种能够自适应分配隐私预算和计算学习率的联邦学习方案(differential privacyfederated learning adaptive gradien...差分隐私被广泛应用于联邦学习中,以保障模型参数的安全,但不够合理的加噪方式会限制模型准确度进一步提高。为此,提出一种能够自适应分配隐私预算和计算学习率的联邦学习方案(differential privacyfederated learning adaptive gradient descent,DP-FLAGD),通过自适应分配隐私预算找到梯度的正确下降方向,并计算合适的学习率以达到最小的损失。同时,DP-FLAGD方案能够为不同隐私需求的用户提供不同的隐私预算,以满足其需求。为评估DP-FLAGD的有效性,在广泛使用的2个数据集MNIST(modiffe national institute of standard and technology)和CIFAR-10上进行相关实验,实验结果表明,DP-FLAGD方案在保证模型参数安全的同时,能够进一步提高模型的准确率。展开更多
自适应波束形成是机载预警雷达数字信号处理的一个关键环节。针对传统最小均方误差(least mean square,LMS)算法在短快拍数条件下的波束形成性能下降以及因迭代震荡易收敛于局部最优值的问题,提出了一种基于机器学习的随机方差减小梯度...自适应波束形成是机载预警雷达数字信号处理的一个关键环节。针对传统最小均方误差(least mean square,LMS)算法在短快拍数条件下的波束形成性能下降以及因迭代震荡易收敛于局部最优值的问题,提出了一种基于机器学习的随机方差减小梯度下降(stochastic variance reduction gradient descent,SVRGD)自适应波束形成方法。首先,建立面阵列接收信号数据模型。其次,基于随机梯度下降原理,引入方差缩减法通过内外循环迭代方式进行梯度修正,以减小随机梯度估计的方差,建立算法模型与实现流程。最后,通过设置平面阵列仿真场景,分析SVRGD自适应波束形成算法在波束形成、抗干扰、收敛速度等方面的性能,验证了该算法在低快拍数、强干扰和强噪声背景下具有的优良能力。展开更多
热晕效应是高能激光大气传输最重要的非线性效应之一。利用激光大气传输四维仿真程序,针对高能固体脉冲激光大气传输的非线性热晕效应,采用常规自适应光学系统与随机并行梯度算法自适应光学系统对其相位补偿进行了数值模拟和分析。结果...热晕效应是高能激光大气传输最重要的非线性效应之一。利用激光大气传输四维仿真程序,针对高能固体脉冲激光大气传输的非线性热晕效应,采用常规自适应光学系统与随机并行梯度算法自适应光学系统对其相位补偿进行了数值模拟和分析。结果表明:当脉冲宽度1 ms,重复频率10 Hz,单脉冲发射功率500 k W时,常规自适应光学系统补偿效果较好;当脉冲发射功率增加或者重复频率增加时,随机并行梯度下降算法自适应光学系统补偿效果较好。展开更多
基金supported by the National Natural Science Foundation of China(1127301761471196)
文摘By applying phase-only technique in array antenna pattern synthesis, antenna arrays can form desired patterns with the use of phase shifters only. A novel phase-only pattern synthesis algorithm is proposed for the passive phased array seeker. This algorithm synthesizes the main beam of the antenna pattern through least-squares approximation, thus minimizing the errors between the actual and the desired main beams. The synthesis problem can be solved by applying gradient-descent optimization. The item for suppressing side lobes is added to the above synthesis problem. To obtain a side lobe level as low as possible, the algorithm assigns different weights to different directions in the side lobe region. The algorithm is run repeatedly and the weights are adjusted adaptively according to the normalized power in the side lobe directions. Detailed examples are presented to demonstrate the accuracy and effectiveness of the proposed approach.
基金Supported by the Science and Technology Innovation 2030 New Generation Artificial Intelligence Major Project(2018AAA0100902)the National Key Research and Development Program of China(2019YFB1705800)the National Natural Science Foundation of China(61973270)。
文摘差分隐私被广泛应用于联邦学习中,以保障模型参数的安全,但不够合理的加噪方式会限制模型准确度进一步提高。为此,提出一种能够自适应分配隐私预算和计算学习率的联邦学习方案(differential privacyfederated learning adaptive gradient descent,DP-FLAGD),通过自适应分配隐私预算找到梯度的正确下降方向,并计算合适的学习率以达到最小的损失。同时,DP-FLAGD方案能够为不同隐私需求的用户提供不同的隐私预算,以满足其需求。为评估DP-FLAGD的有效性,在广泛使用的2个数据集MNIST(modiffe national institute of standard and technology)和CIFAR-10上进行相关实验,实验结果表明,DP-FLAGD方案在保证模型参数安全的同时,能够进一步提高模型的准确率。
文摘热晕效应是高能激光大气传输最重要的非线性效应之一。利用激光大气传输四维仿真程序,针对高能固体脉冲激光大气传输的非线性热晕效应,采用常规自适应光学系统与随机并行梯度算法自适应光学系统对其相位补偿进行了数值模拟和分析。结果表明:当脉冲宽度1 ms,重复频率10 Hz,单脉冲发射功率500 k W时,常规自适应光学系统补偿效果较好;当脉冲发射功率增加或者重复频率增加时,随机并行梯度下降算法自适应光学系统补偿效果较好。
