Hyperparameter optimization method based on dynamic Bayesian with sliding balance mechanism in neural network for cloud computing

Journal of Cloud Computing

Advances, Systems and Applications

Table 4 Comparison of different K value

K parameter	Results in different search progress (AP50 ± Variance)
K parameter	1/4	2/4	3/4	1
K = 1	0.449 ± 0.006	0.461 ± 0.003	0.465 ± 0.007	0.470 ± 0.005
K = 3	0.453 ± 0.003	0.461 ± 0.005	0.465 ± 0.002	0.477 ± 0.002
K = 5	0.459 ± 0.008	0.459 ± 0.008	0.463 ± 0.005	0.468 ± 0.004
K = 10	0.458 ± 0.007	0.460 ± 0.004	0.462 ± 0.002	0.463 ± 0.002