Loading...

Deep Learning and Optimal Control

Ehsani, Pouya | 2023

30 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56358 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Fotouhi, Morteza
  7. Abstract:
  8. Our main focus in this thesis is on optimal control methods for the analysis of deep neural networks, such as the supervised learning problem. A neural network with a large number of layers can be modeled with an ordinary differential equation, whose control parameters play the role of intermediary functions in the neural network. This model gives us a more powerful tool to analyze the asymptotic behavior of the neural network. Also, in this thesis, the problems of numerical implementation of these methods will be discussed
  9. Keywords:
  10. Deep Learning ; Deep Neural Networks ; Machine Learning ; Optimal Control

 Digital Object List

 Bookmark

No TOC