研究RBF神经网络的一种具有对训练数据集中离群点的鲁棒性的快速学习算法。使用相减聚类(Subtractive Clustering,SC)法选择RBF网络隐结点的中心,以定标鲁棒损失函数(Scaled Robust Loss Function,SRLF)为目标函数,采用梯度下降法调整...研究RBF神经网络的一种具有对训练数据集中离群点的鲁棒性的快速学习算法。使用相减聚类(Subtractive Clustering,SC)法选择RBF网络隐结点的中心,以定标鲁棒损失函数(Scaled Robust Loss Function,SRLF)为目标函数,采用梯度下降法调整隐结点的宽度和网络权值,从而使RBF网络的学习过程不受离群点的影响,并且能够快速收敛。实验结果表明了RBF神经网络的这一学习算法的优越性。展开更多
We study the kinetic behavior of a two-species aggregation-migration model in which an irreversible aggregation occurs between any two clusters of the same species and a reversible migration occurs simultaneously betw...We study the kinetic behavior of a two-species aggregation-migration model in which an irreversible aggregation occurs between any two clusters of the same species and a reversible migration occurs simultaneously between two different species. For a simple model with constant aggregation rates and with the migration rates KA(i;j) =K'A (i;j) ∝ijv1 and KB(i; j) = K'B (i; j) ∝ ijv2, we find that the evolution behavior of the system depends crucially on the values of the indexes v1 and v2. The aggregate size distribution of either species obeys a conventional scaling law for most cases. Moreover, we also generalize the two-species system to the multi-species case and analyze its kinetic behavior under the symmetrical conditions.PACS numbers: 82.20.-w, 05.40.-a, 68.43.Jk, 89.75.展开更多
For a given compactly supported scaling fun ct ion supported over [0,3]×[0,3], we present an algorithm to construct compac t ly supported orthogonal wavelets. By this algorithm, the symbol function of the associa...For a given compactly supported scaling fun ct ion supported over [0,3]×[0,3], we present an algorithm to construct compac t ly supported orthogonal wavelets. By this algorithm, the symbol function of the associated wavelets can be constructed explicitly.展开更多
文摘研究RBF神经网络的一种具有对训练数据集中离群点的鲁棒性的快速学习算法。使用相减聚类(Subtractive Clustering,SC)法选择RBF网络隐结点的中心,以定标鲁棒损失函数(Scaled Robust Loss Function,SRLF)为目标函数,采用梯度下降法调整隐结点的宽度和网络权值,从而使RBF网络的学习过程不受离群点的影响,并且能够快速收敛。实验结果表明了RBF神经网络的这一学习算法的优越性。
文摘We study the kinetic behavior of a two-species aggregation-migration model in which an irreversible aggregation occurs between any two clusters of the same species and a reversible migration occurs simultaneously between two different species. For a simple model with constant aggregation rates and with the migration rates KA(i;j) =K'A (i;j) ∝ijv1 and KB(i; j) = K'B (i; j) ∝ ijv2, we find that the evolution behavior of the system depends crucially on the values of the indexes v1 and v2. The aggregate size distribution of either species obeys a conventional scaling law for most cases. Moreover, we also generalize the two-species system to the multi-species case and analyze its kinetic behavior under the symmetrical conditions.PACS numbers: 82.20.-w, 05.40.-a, 68.43.Jk, 89.75.
文摘For a given compactly supported scaling fun ct ion supported over [0,3]×[0,3], we present an algorithm to construct compac t ly supported orthogonal wavelets. By this algorithm, the symbol function of the associated wavelets can be constructed explicitly.
