经过长期不懈努力,科学家认为可以从仿制人脑神经系统的结构和功能出发,研究人类智能活动和认识现象。然而,客观现实世界是纷繁复杂的,非线性情况随处可见,人脑神经系统更是如此。为了更好地认识客观世界,我们必须对非线性科学进行研究。人工神经网络作为一种非线性的、与大脑智能相似的网络模型,就这样应运而生了。因此,首先对人工神经网络进行了概述;而后重点描述BP网络模型,对其基于弹性BP算法的BP网络设计与实现;最后,对网络的训练和测试进行了简单的分析。 After long-term and unremitting efforts, scientists think that we can study human intelligence activities and cognitive phenomena from the structure and function of the imitated human brain nervous system. However, the objective real world is complicated and nonlinear situations can be found everywhere, even more so in the human brain. In order to better understand the objective world, we must study non-linear science. Artificial neural network as a nonlinear, similar to the brain intelligence network model, so came into being. Therefore, firstly, the artificial neural network is outlined; then, the BP network model is mainly described, and its BP network design and implementation based on the elastic BP algorithm are described. Finally, the network training and testing are briefly analyzed.