1981年芬兰 一种自组织特征映射网 ， 又称 Kohonen 网 。 Kohonen 认为 ，一个神经网络接受外界输入模式时， 将会分为不同的对应区域， 各区域对输入模式具有不同的响应特征(In 1981, a self organizing feature mapping network, also known as Kohonen network, was used in Finland. Kohonen thinks that when a neural network accepts external input mode, it will be divided into different corresponding regions. Each region has different response characteristics to input mode.)