通过分析函数的一阶导数与二阶导数图像的特征，提出了一种含有权值的图像边缘锐化的新算法。
By analyzing the characteristics of the function's once and quadratic differential coefficient's image, a new algorithm of images' edge sharpening which contains weights.
在特征集的基础上，讨论了其参数导数的构成情况，用有限个点和函数表示了无穷个参数导数的情形。
Based on characteristic set, the case of infinity parameters is described by using of finite value and functions.
当网络连接权值矩阵的最小特征值大于激活函数导数的倒数时，网络并行收敛。
When the minimal eigenvalue of connection weights matrix is greater than the reciprocal of derivation of its neuron activation function, the network will be convergent in parallel update mode.
应用推荐