When I first read about neural networks, I learned that Backpropagation is the algorithm used to train the neural network. I am interested if there are other alternatives (or better?) to BP.

What are the other training algorithms used in NN? And is BP is the best one, and that's why almost everyone uses it for training the NN model?


Yes, some alternatives are feedback-alignment (FA), Direct Feedback Alignment (DFA) and Indirect Feedback Alignment (IFA).

  • $\begingroup$ Thank you, I will look into those, why BP has such a good reputation in comparison with these alternatives? $\endgroup$
    – U. User
    Nov 4 '18 at 17:06
  • $\begingroup$ Because it dates back to 70s, is quite simple and works great! $\endgroup$ Nov 4 '18 at 23:05
  • $\begingroup$ Thank very much. One last question if you may, is the code of these alternatives algorithms available? Meaning do you know of libraries that may has these code, like weka or toolbox in matlab? $\endgroup$
    – U. User
    Nov 5 '18 at 11:16

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.