Research and Application of Deformation Prediction Model for Deep Foundation Pit Based on LSTM

Algorithm 5

RMSProp algorithm.

Require: set the initial learning rate to , the decay rate is set to , and the initial parameter is set to

Require: set the initial gradient accumulative value to 0, and the value of the initial constant is 10^-8

While stop condition not satisfied do

Randomly extract samples from the training set, and is the true value corresponding to .

Calculate the average gradient of samples:

Square of accumulated value of historical gradient:

Update gradient value: (element operation)

Parameter updating:

End while