基于神经网络的逻辑计算

Neural-Network-Based Logic Computation

神经网络得到了越来越广泛的应用,目前它主要应用于模式识别和联想记忆等领域。我们通过研究发现,神经网络同样可以很好地应用于逻辑计算。本文提出了可以完成任何逻辑计算的通用模型,根据这种模型构造的神经网络可以实现复杂的逻辑计算,并且能够根据退化了的数据进行精确的逻辑计算。

Neural networks are finding many areas of applications. At present, it ismainly used in pattern recognition and associative recall. But in this paper, we present auniversal logic module able to accomplish any logic computations. The interesting aspect ofdoing logic operations on neural networks is the ability to accomplish precise logical com-putations on highly degraded data.