Deep Learning and Optimal Control

Please enable javascript in your browser.

Ehsani, Pouya | 2023

30 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 56358 (02)
University: Sharif University of Technology
Department: Mathematical Sciences
Advisor(s): Fotouhi, Morteza
Abstract:
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
Keywords:
Deep Learning ; Deep Neural Networks ; Machine Learning ; Optimal Control

No TOC