A LSTM-RNN-Based Fiber Optic Gyroscope Drift Compensation

Algorithm 3

LSTM-RNN. Algorithm procedure of the LSTM-RNN model.

(i)	Initialization: Time steps H
(ii)	Input: Training samples
(iii)	for M = 1, 2, 3, ^… do
(iv)
(v)
(vi)
(vii)
(viii)
(ix)
(x)	M = M + 1
(xi)	end for
(xii)	is input connection, is recurrent connection, and is peephole connection, i = 1, 2, 3, and 4. is the sigmoid function.