I want to use artificial neural network(ANN) for solving non-convex optimisation problems. How do I map the constraints and the objective functions in the ANN architecture?

  • 1
    $\begingroup$ can you share more details about the function you're trying to optimize? neural nets do solve non-convex problems - the standard "sum-of-squares" (= max-likelihood if the target vectors are normally distributed) error function is non-convex (because the function computed by the ANN is nonlinear), and what you've converged to after training is a local minimum. $\endgroup$ – GoHokies Aug 2 '18 at 20:19

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.