Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application

HIGHLIGHTS

SUMMARY

The proposed OBSCA-FS algorithm was tested for the dropout rate and validated against several cutting-edge metaheuristics approaches. The proposed OBSCA-FS driven CNN was also compared to other cutting-edge, non-metaheuristics approaches, including SVM + RFE, Vanilla preprocessing + shallow CNN, LeNet-5, VGG19 and DenseNet. The presented findings indicate that the proposed OBSCA-FS approach obtained the best average | Vol:(1234567890) 12:6302 | accuracy and the dropout probability of 0.43, clearly outperforming all traditional and metaheuristics approaches included in the research. Once more the proposed OBSCA-FS significantly outperformed both SCA . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.