Neuroinformatics Group

Universität Bielefeld › Technische Fakultät › NI

AGNI Theses

Deep Vision

 

Figure: Facebook AI [1]

 

This thesis / project will focus on practical applications of state of the art in computer vision [1][2] to detect objects and segment images [3][4][5][6]. 

[1] https://ai.facebook.com/blog/dino-paws-computer-vision-with-self-supervised-transformers-and-10x-more-efficient-training)

[2] https://www.youtube.com/watch?v=h3ij3F3cPIk&pp=qAMBugMGCgJkZRAB

[3] https://youtu.be/SfqN-Hc5two?t=612

[4] https://www.aicrowd.com/challenges/food-recognition-challenge

[5] https://www.aicrowd.com/challenges/global-wheat-challenge-2021

[6] https://youtu.be/HS1wV9NMLr8

 

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, Datamining, Neural Networks, 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
Error-microscope to accelerate piano learning

Playing a musical instrument well is a skill that many people are pursuing over years. What makes it particularly difficult is the absence of a teacher to provide feedback and encouragement.  While practicing, we commonly neither choose the best practice strategies, nor are we capable of self-analyzing our performance.

Datamining, active
Recommender Systems for piano practice (multiple topics)

dexmo

 

 

 Recommender systems are being ubiquitously used to optimally  couple users and products. The goal of this project is to employ standard methods used to produce recommendations [1,4]

Datamining, active

Login

Neuroinformatics Group 2017

© 2017 Universität Bielefeld