I want to add comparison of accuracy section in my study report on CNN Architecture for a medical data. I have already added the comparison by VGG 16, AlexNet etc. Is it a standard to compare the accuracy of the CNN Architecture by increasing the number convolution layers or dropout percentage? Is there any parameter which is important to analyze and universally accepted in the literature?

Thanks in advance


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.