The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

8

Jun

Improving the performance of Shallow Neural Networks using norm-preserving regularization

8 June 2026 09:15 to 10:00 |

Master Thesis presentation by Daniel Stoopendahl

Title:  Improving the performance of Shallow Neural Networks using norm-preserving regularization
Author: Daniel Stoopendahl
Date & Time: June 8th, 9:15-10:00
Location: Seminar Room M 3170-73 in the M-building, LTH
Supervisor: Pontus Giselsson
Examiner:  


Abstract:

The thesis analyses a new method of regularization. It looks into performance gains on Shallow Neural Networks as well as why it works.

About the event

Location:

Seminar Room M 3170-73 in the M-building, LTH

Contact:

pontus [dot] giselsson [at] control [dot] lth [dot] se