0
$\begingroup$

I'm working on an image classification project. I just want to know some basic level clarification. how does a neural network learn only the relevant features based on the label?

Let's say I'm creating two folders like flower and leaf and putting all the images into the folder. how deep learning techniques learn only flower pixels because some flower images have leaf also. how it will learn only flower features.

$\endgroup$
1
  • 1
    $\begingroup$ very broad and vague question. In reality people only know that by backpropagation the weights are learned. it has been suggestd that for CNNs the first layers represent types of Gabor filters, but again it is not always the case $\endgroup$
    – Nikos M.
    Jun 20 at 18:09

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.