二值神经网的逻辑理论

Logic Theory of Binary Neural Networks

提出了二值神经网（ＮＮＳ）的逻辑理论，它包括二状态判决、弱推理、推理规则、规则类型和强度、一致和矛盾等。该理论表明：神经网是自主的、开放的、柔性限制的和自适应的约束满足网；神经网运行的根本原因是网络中存在着优势矛盾。

We foresee the applicability of binary neural networks to a number of engineering problems. We feel that its logic theory should be studied so as to make it useful in engineering inthe future. Past researchers have only actively studied computational ability of binary neuralnetworksOur study reveals that, as neural networks Can be viewed as constraint satisfaction networks (CSNs), it needs an inherent logic theory consistiong of two-state (excitatory stateand inhibitory state ) deciSions, weak inference, rule types (excitatory and inhibitory),strength identity and contradiction (superior and inferior). Superior contradiction is filllydiscussed and defined in the full paper. The process by which a neural network seeks a solution corresponds to eliminating of the superior contradiction. We are of the opinion that neural networks can be described as self-made, open, flexible, and self-adaptive CSNs