算法将网络训练看成是求解一个优化问题，网络权是优化变量，而先验知识则是优化问题中的约束项。
It takes the network training process as to solve a nonlinear optimization problem. The network weights are optimization variables and prior-knowledge is the constraint.
设计的变量约束网是一个能够综合表达变量间各种约束关系的网络结构。
The variable constraint net built in this paper is a network structure, which can represent different kinds of constraint relation between variables.
设计的变量约束网是一个能够综合表达变量间各种约束关系的网络结构。
The variable constraint net built in this paper is a network structure, which can represent different kinds of constraint relation between variables.
应用推荐