在人工免疫系统反向选择机理的基础上，分析了二进制反向选择算法的缺点及采用实值编码的优点。
The shortcoming of binary negative selection algorithm and the excellence of real value coding based on the negative selection mechanism of artificial immune systems is analysed.
经过我选择了多层感知和标准的反向传播训练算法的研究。
After some research I have chosen a multilayer perceptron and standard back-propagation algorithm for training.
应用推荐