lunduniversity.lu.se

Digit@LTH

Faculty of Engineering, LTH

Denna sida på svenska This page in English

Digit@LTH: Events

CS MSc Zoom Presentation 1 June 2020!

Föredrag

From: 2020-06-01 14:00 to: 15:00
Place: https://lu-se.zoom.us/j/67775257943
Contact: birger [dot] swahn [at] cs [dot] lth [dot] se
Save event to your calendar


One Computer Science MSc thesis to be presented on 1 June 2020 via Zoom

Monday, 1 June there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place via Zoom at: https://lu-se.zoom.us/j/67775257943

Note to potential opponents: Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname [dot] lastname [at] cs [dot] lth [dot] se). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.


14.00-15.00

Presenters: Oskar Holmberg, Erik Munkby
Title: Product Design using Generative Neural Networks
Examiner: Jacek Malec
Supervisors: Elin Anna Topp (LTH), Johnny Dang (Jayway)

Generative Neural Networks have for many years proven successful at producing continuous data, e.g. images or music. When it comes to discrete data such as text or speech, comparable success has to our knowledge not yet been found. In this study we tackle some of the difficulties of generating discrete data in an attempt to assemble wardrobe configurations from a set of products. This study combines the two Generative Adversarial Network archetypes Auxiliary Classifier and Deep Convolutional to render wardrobe configurations presented in a 3D digital environment. The study shows that the approach can be considered a viable option for automatic generation of modular wardrobes.