University of Twente Student Theses
Gradient Descent with Random Minibatches in the Linear Model
Mash'Al, Yazan (2024) Gradient Descent with Random Minibatches in the Linear Model.
|
PDF
1MB |
| Abstract: | This thesis explores the dynamics and convergence properties of gradient descent algorithms when integrated with dropout techniques and random minibatch sampling in the context of linear regression. Dropout, a form of regularization, and minibatch gradient descent are both crucial in developing robust machine learning models that generalize well to unseen data. This paper aims to showcase the theoretical properties and practical implications of using these two methods. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 31 mathematics, 54 computer science |
| Programme: | Applied Mathematics BSc (56965) |
| Link to this item: | https://purl.utwente.nl/essays/100665 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page