Position Control of Magnetic Levitation Ball Based on an Improved Adagrad Algorithm and Deep Neural Network Feedforward Compensation Control

Table 5

Iteration times of the two algorithms under the same iteration result.

No.	Standard	Adagrad iterations	Improve Adagrad iterations
1	1.0648	273	10
2	0.3442	2997	655
3	3.5184	96	8
4	2.1352	500	4
5	3.6049	364	6