Neuroinformatics Group

Universität Bielefeld › Technische Fakultät › NI

AGNI Theses

Music composition with GFlowNetworks

  

Employing Generative AI to compose music has been enormously successful (magenta from google, aws deep composer from amazon, etc). 

Neural Networks, Software Tools, active
Multi-agent dense traffic on complex railway networks

 This challenge tackles a key problem in the transportation world: How to efficiently manage dense traffic on complex railway networks? This is a real-world problem faced by many transportation and logistics companies around the world such as the Swiss Federal Railways and Deutsche Bahn. We are developing an AI agent capable of solving such problem. 

If you would like to know more about this thesis / project opportunity, please contact: 
Dr. Andrew Melnik <andrew.melnik(at)uni-bielefeld.de>
Attentive Interfaces, Datamining, Neural Networks, Software Tools, active
Deep Face Editing with StyleGAN

  Figure: animation of faces from old family photos using Deep Learning approaches

(source https://www.myheritage.com/deep-nostalgia)

This thesis / project will focus on practical applications of state of the art style generative adversarial network models (StyleGAN) [see References here].

If you would like to know more about this thesis / project opportunity, please contact: Dr. Andrew Melnik <andrew.melnik(at)uni-bielefeld.de>

Attentive Interfaces, Computer Vision, Neural Networks, Software Tools, active
Physical Reasoning Artificial Intelligence

 Try to solve the following physical puzzles to get an idea about this thesis / project: https://brainitongame.com  and  https://phyre.ai

We are developing an AI agent capable of solving such physical reasoning tasks. If you would like to know more about this thesis / project opportunity, please contact: 
Dr. Andrew Melnik <andrew.melnik(at)uni-bielefeld.de>

Attentive Interfaces, Cognitive Robotics, Computer Vision, Neural Networks, Software Tools, active

Login

Neuroinformatics Group 2017

© 2017 Universität Bielefeld