RNN应用于输入数据具有依赖性且是序列模式时的场景，即前一个输入和后一

RNN applied to input data having a time dependent sequence and a scene mode, i.e., after a previous input and input are related. It is different from the structure FCNN, RNN of the hidden layer is cyclic. This indicates that the value of the hidden layer depends not only on the current input values, but also on the value of the previous time the hidden layer

RNN applies to scenes where input data is dependent and is sequence pattern, i.e. the previous input is related to the latter input. Unlike the FCNN structure, the hidden layer of rnN is circular. This indicates that the value of the hidden layer depends not only on the current input value, but also on the value of the hidden layer at the previous time

RNN is applied to the scenario where the input data is dependent and sequential, i.e. the previous input is related to the latter. Unlike FCNN, the hidden layer of RNN is cyclic. This indicates that the value of the hidden layer depends not only on the current input value, but also on the value of the previous hidden layer<br>