人工神经网络（Artificial Neural Networks，ANN）系统是 20 世纪 40 年代后出现的。它是由众多的神经元可调的连接权值连接而成，具有大规模并行处理、分布式信 息存储、良好的自组织自学习能力等特点。BP（Back Propagation）算法又称为误差 反向传播算法，是人工神经网络中的一种监督式的学习算法。BP 神经网络算法在理 论上可以逼近任意函数，基本的结构由非线性变化单元组成，具有很强的非线性映射能力。(The Artificial Neural Networks (ANN) system appeared after 1940s. It is made up of a number of neurons with adjustable connection weights. It has the characteristics of massively parallel processing, distributed information storage, and good self-organizing and self-learning ability. The BP (Back Propagation) algorithm, also known as the error back propagation algorithm, is a supervised learning algorithm in the artificial neural network. The BP neural network algorithm can approximate any function in theory, and the basic structure is composed of nonlinear change units, and has a strong nonlinear mapping ability.)