I am interested in finding out references that apply dynamical systems analysis to develop the "theory" of deep learning, specifically (say) feedforward deep neural nets. The only paper I seem to have found is "Dynamics of learning in deep linear neural networks" from 2014.

I would like to understand if dynamical systems approach makes sense in developing the theory and analysis of deep learning methods.

  • $\begingroup$ statistical analysis theory & gradient descent concepts are prob more applicable overall/ in general, but also its an emerging area of study... $\endgroup$ – vzn Apr 16 '15 at 15:29

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.