逻辑电路的神经网络

Neural Networks for Logic Circuits

Ｍ．Ｌ．Ｂｕｓｈｎｅｌ教授和作者给出了ＮＯＴ，ＡＮＤ，ＯＲ，ＮＡＮＤ，ＮＯＲ，ＸＯＲ和ＸＮＯＲ门的神经网络．以这些门的神经网络为基础，可构成任何逻辑电路的神经网络．由此，将电路的相容信号转换为平方伪布尔函数的全局极小．从而。

Porf. M.L.Bushnell and the authors presented the neural networks for NOT,AND,OR,NAND,NOR,XOR and XNOR gates. Using these neural networks, we can construct the neural networks of any logic circuits. From this, the consistent signals in the logic circuits will be transformed into the global minimal points of quadratic pseudo Boolean functions. Thus the neural network application in the field of circuit modeling and automatic test pattern generation can be widened.