本文把Kohonen的自组织特征映射人工神经网络用于解决集成电路设计中两端线网的布局问题——二次分配问题.与最小割算法相比,对于规模较小的电路,神经网络方法能以较快的速度得到最优布局.但当电路规模增大时,得到好的布局需要较长的计算时间. In this paper, Kohonen’s self-organizing feature map artificial neural network is used to solve the problem of the second-distribution problem of the two-end net in the integrated circuit design. Compared with the minimum cut algorithm, for the smaller circuit, the neural network method can Faster speed to get the best layout, but when the circuit size increases, get a good layout requires a longer calculation time.