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

Table 3

Benchmark functions used in experiments.

No.	Range	Function	Formulation
1	[−100, 100]	Bohachevsky2
2	[−4.5, 4.5]	Beale
3	[−100, 100]	Bohachevsky1
4	[−5, 5]	Six-hump camel back
5	[−100, 100]	Bohachevsky3