I want to know what it is, and how it is any different from ensembling?

Suppose, I want to achieve high accuracy in classification and segmentation, for a specific task, if I use different networks, such as CNN, RNN, etc to achieve this, is this called an end to end model? (architecture?) or not?

  • end-to-end = all parameters are trained jointly (vs. step-by-step)
  • ensembling = several classifiers are trained independently, each classifier makes a prediction, and all predictions are combined into one using some strategy (e.g., take the most common prediction across all classifiers).
| cite | improve this answer | |
  • $\begingroup$ Thank you very much. basically I want to achieve a high accuracy in classification and segmentation, and I am willing to use deep learning methods (architectures?) and form one complete model out of all of these methods and architectures. Is this called end to end? is is it considered ensembling? $\endgroup$ – Rika Jul 16 '16 at 18:44
  • $\begingroup$ @Hossein are your classifiers trained independently? $\endgroup$ – Franck Dernoncourt Jul 16 '16 at 18:45
  • $\begingroup$ Thats a nice question, I have no idea! How does that affect us? you know I'm researching at the moment, and I have no idea what I'm going to be dealing with. So I am trying to get a good grasp on the concepts I see in literature. $\endgroup$ – Rika Jul 16 '16 at 18:48
  • $\begingroup$ @Hossein it only affects the name :) $\endgroup$ – Franck Dernoncourt Jul 16 '16 at 18:52
  • 1
    $\begingroup$ @Hossein: If you train the CNN at the same time as the RNN, then it's end-to-end training. $\endgroup$ – Franck Dernoncourt Jul 16 '16 at 19:03

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.