度信念网络是一个概率生成模型，与传统的判别模型的神经网络相对，生成模型是建立一个观察数据和标签之间的联合分布，对P(Observation|Label)和 P(Label|Observation)都做了评估，而判别模型仅仅而已评估了后者，也就是P(Label|Observation)。(The degree belief network is a probability generation model. Compared with the neural network of the traditional discriminant model, the generation model is to establish a joint distribution between observation data and labels, and to do both P (Observation|Label) and P (Label|Observation).The evaluation, and the discriminant model has only evaluated the latter, that is, P (Label|Observation).)