Versions Compared


  • This line was added.
  • This line was removed.
  • Formatting was changed.


During training we optimize the loss function, i.e. reduce the error between actual and predicted values. Since we deal with a binary classification problem, the can take on just two values, (for hypothesis ) and Image Removed = 1 (for hypothesis ).

A popular algorithm to optimize the weights consists of iteratively modifying the weights after each training observation or after a bunch of training observations by doing a minimization of the loss function.