The feature extracted by various layers of a CNN

#1

Hi ,
What I have learnt by now is that the Convolution base network.
The intial layers have a very small receptive field and therefore extract very fine features[which are not able to generalize well on test data].
But as we go deeper into the neural network…the neurons have higher receptive field.

But in the video Prateek Sir has quoted that the intial layers capture very generic features.

Therefore we need to modify the higher layers(deeper layers which extract very high level features.

Kindly clear this doubt

#2

Hey @chiragwxN, i hope i already cleared your doubt, over whatsapp.

Plz mark the doubt as resolved :blush:

#3

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.