Could changing the order of convolution layers in a CNN improve accuracy or training time?


Conventionally, CNN layers downsample over and over, which enables them to capture details at different levels of abstractions. Usually, it is observed that the initial layers do nothing more than detecting edges, or filtering color channels; the combinations of these edges are what we perceive as 'features'.

If you reverse the order, you essentially are changing sampling modes down the line. CNNs detect by 'downsampling' the inputs and therefore 'extracting' features.

It may not work as expected!

| improve this answer | |
  • $\begingroup$ Thank you that was a clear answer $\endgroup$ – AMEL BENAIDA Apr 23 '19 at 18:55

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.