Elman神经网络是 J. L. Elman于1990年首先针对语音处理问题而提出来的，是一种典型的局部回归网络( global feed forward local recurrent)。Elman网络可以看作是一个具有局部记忆单元和局部反馈连接的递归神经网络。(The Elman neural network, which was first proposed by j. l. Elman in 1990 for voice processing, is a typical global feed forward local solution. The Elman network can be regarded as a recursive neural network with local memory unit and local feedback connection.)