immunity

说明：  针对实际对象数学模型不明确而难以控制的问题,采用人工免疫网络的离散模 型与学习算法,将人工免疫系统与神经网络结构的优势相结合,提出了一种基于人工免疫 网络的模式识别算法,构造了对象识别的人工免疫网络模型.该算法综合了网络节点的定 位与参数调整以及对基函数的平滑因子实施调谐等功能,有效地解决了径向基函数 (RBF)神经网络模式识别的两个阶段任务,使模式识别的精度有较大的改进.采用两个不 同对象函数进行的仿真试验表明,该算法具有快速收敛性与较高的准确性. (Mathematical model for the actual object is not clear and difficult to control the problem, the use of artificial immune network model and the discrete learning algorithm, artificial immune systems and neural networks combine the advantages of structure, an artificial immune network based on pattern recognition algorithms, Construction of the object identified by artificial immune network model. the algorithm is a combination of network nodes to adjust the position and parameters as well as the basis function implementation of the smoothing factor, tuning and other functions, to effectively solve the Radial Basis Function (RBF) neural network pattern recognition of two phase of the task, so that the accuracy of pattern recognition have greater improvements. the use of two different object functions of the simulation tests show that the algorithm has fast convergence and higher accuracy.)