时序预测 | Matlab实现ARIMA-LSTM差分自回归移动差分自回归移动平均模型模型结合长短期记忆神经网络时间序列预测
%% lstm
layers = [ ...
sequenceInputLayer(inputSize) %输入层设置
lstmLayer(numhidden_units1,'name','hidden1') %学习层设置
dropoutLayer(0.2,'name','dropout_1')
lstmLayer(numhidden_units2,'name','hidden2')
dropoutLayer(0.3,'name','dropout_2')
lstmLayer(numhidden_units3,'name','hidden3')
dropoutLayer(0.2,'name','dropout_3')
fullyConnectedLayer(outputSize) % 全连接层设置
regressionLayer('name','out')];
%% trainoption(lstm)
[1] https://blog.csdn.net/article/details/126072792?spm=1001.2014.3001.5502
[2] https://blog.csdn.net/article/details/126044265?spm=1001.2014.3001.5502