在对情感神经网络进行研究时，参照了情感心理学的内容要求，而且也相对地加入了情感智能中的情感因子。在普通神经网络结构中添加情感因素分量建立情感神经网络模型，以此改进神经网络的学习和决策过程，构建包括情感神经元在内的各个神经元输入输出关系，建立情感神经网络结构，推导出情感神经网络学习算法。把该算法用于信用卡评估工作，通过实验证明提出的情感神经网络算法的分类效果明显优于传统方法，好客户和坏客户的识别率均为100%，在一定程度上提高了模型的分类精度。%The emotional neural network is researched by referring the content requirement of emotion psychology,and the emotional factor in emotional intelligence is added relatively. The emotional factor component is added into the common neural network structure to establish the emotional neural network model,which can improve the learning and decision⁃making process⁃es of the neural network. In this paper,the input and output relations of each neuron are constructed,including the emotion neu⁃ron. The emotional neural network structure was established to deduct the learning algorithm of emotional neural network. The al⁃gorithm is applied to the credit card assessment. The experimental results show that the classification effect of the proposed emo⁃tional neural network algorithm is obviously better than that of the traditional method,and the recognition rate of good customer and bad customer can reach up to 100%,and the model classification accuracy is improved to a certain extent.
展开▼
