Is there any structure for fully connected layers that could learn square/cube operations?
As far as I known, fully connected layers could learn linear representation well. But for specific no-linear representation it remains a mystery. 2^2 = 4 2^3 = 8

  • 1
    $\begingroup$ This question is a bit of mystery to me... Why do you need neural networks to learn cubic or quadratic function? $\endgroup$ – Jan Kukacka Aug 22 '18 at 6:40
  • $\begingroup$ @JanKukacka Because I want to interpret a model, I think this model may has implemented square operation. But this model is a bit complex. $\endgroup$ – Mark Aug 22 '18 at 6:50
  • $\begingroup$ Are you asking if a neural network with linear activations can learn the square function, or something else? $\endgroup$ – Coolness Aug 22 '18 at 10:25

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.