Addressing Overfitting Problem in Deep Learning-Based Solutions for Next Generation Data-Driven Networks

Table 1

Comparison of error rate (%) and retention probability of 4 methods in MNIST data set.

Retention probability	0.1	0.2	0.3	0.4	0.5	0.6	0.7	0.8	0.9
ICNN	6.36	6.36	6.36	6.36	6.36	6.36	6.36	6.36	6.36
H_Dropout	7.27	6.85	6.50	6.32	6.30	6.31	6.38	6.40	6.51
SP	2.23	2.17	2.10	2.08	2.13	2.26	2.31	2.37	2.49
MDWS	2.21	2.15	2.03	1.95	1.63	1.88	2.19	2.26	2.27