1
$\begingroup$

Neural network is established as an universal approximator of all machine learning models. Further, double descent phenomenon in a neural network propagates the journey of regression to interpolation via interpolating point. Is it possible to propagate it further to generation modelling?

Improve this question
$\endgroup$
2
  • 1
    $\begingroup$ This might be possible via multi-modal neural networks. See Multimodal Deep Learning $\endgroup$
    – patagonicus
    Commented Aug 9 at 4:21
  • $\begingroup$ May you explain further? $\endgroup$
    – Lakshman
    Commented Aug 9 at 4:28

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.