The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We...The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.展开更多
基于深度置信网络(DBN)对信号双谱对角切片(BDS)结构特征进行学习,实现低截获概率(LPI)雷达信号识别。该方法首先建立基于受限玻尔兹曼机(RBM)的DBN模型,对LPI雷达信号的BDS数据进行逐层无监督贪心学习,然后运用后向传播(BP)机制在有监...基于深度置信网络(DBN)对信号双谱对角切片(BDS)结构特征进行学习,实现低截获概率(LPI)雷达信号识别。该方法首先建立基于受限玻尔兹曼机(RBM)的DBN模型,对LPI雷达信号的BDS数据进行逐层无监督贪心学习,然后运用后向传播(BP)机制在有监督学习方式下根据学习误差对DBN模型参数进行微调,最后基于该BDS-DBN模型实现未知信号的分类和识别。理论分析和仿真结果表明,信噪比高于8 d B时,基于BDS和DBN的识别方法对调频连续波(FMCW),Frank,Costas,FSK/PSK 4类LPI信号的综合识别率保持在93.4%以上,高于传统的主成分分析加支持向量机法(PCA-SVM)和主成分分析加线性判别分析法(PCA-LDA)。展开更多
针对获取水声目标有类标样本困难且代价高昂的水声目标小样本识别问题,提出了基于混合正则化深度置信网络(hybrid regularization deep belief network,HR-DBN)的水声目标深度特征学习及识别方法。该方法首先提出了混合2种正则化策略的...针对获取水声目标有类标样本困难且代价高昂的水声目标小样本识别问题,提出了基于混合正则化深度置信网络(hybrid regularization deep belief network,HR-DBN)的水声目标深度特征学习及识别方法。该方法首先提出了混合2种正则化策略的深度置信网络进行水声目标深度特征学习。第一种正则化策略是利用最大互信息组正则化项修正目标函数,提高隐含层的稀疏度;第二种正则化策略是利用大量无类标样本获得有关水声目标的普遍特性的描述和先验知识,引导特征学习。最后利用少量有类标样本对网络进行全局优化,构建识别系统,提高水声目标识别正确率。利用2类实测舰船辐射噪声数据进行验证实验,实验结果表明,提出的方法可以提取描述水声目标的深度特征,提高水声目标识别正确率。展开更多
文摘The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.
文摘基于深度置信网络(DBN)对信号双谱对角切片(BDS)结构特征进行学习,实现低截获概率(LPI)雷达信号识别。该方法首先建立基于受限玻尔兹曼机(RBM)的DBN模型,对LPI雷达信号的BDS数据进行逐层无监督贪心学习,然后运用后向传播(BP)机制在有监督学习方式下根据学习误差对DBN模型参数进行微调,最后基于该BDS-DBN模型实现未知信号的分类和识别。理论分析和仿真结果表明,信噪比高于8 d B时,基于BDS和DBN的识别方法对调频连续波(FMCW),Frank,Costas,FSK/PSK 4类LPI信号的综合识别率保持在93.4%以上,高于传统的主成分分析加支持向量机法(PCA-SVM)和主成分分析加线性判别分析法(PCA-LDA)。
文摘针对获取水声目标有类标样本困难且代价高昂的水声目标小样本识别问题,提出了基于混合正则化深度置信网络(hybrid regularization deep belief network,HR-DBN)的水声目标深度特征学习及识别方法。该方法首先提出了混合2种正则化策略的深度置信网络进行水声目标深度特征学习。第一种正则化策略是利用最大互信息组正则化项修正目标函数,提高隐含层的稀疏度;第二种正则化策略是利用大量无类标样本获得有关水声目标的普遍特性的描述和先验知识,引导特征学习。最后利用少量有类标样本对网络进行全局优化,构建识别系统,提高水声目标识别正确率。利用2类实测舰船辐射噪声数据进行验证实验,实验结果表明,提出的方法可以提取描述水声目标的深度特征,提高水声目标识别正确率。
