Student Area

This is the right page if you are looking for a bachelor's project.

And it is also the right page if you are looking for a master's project.

Office hours are before/after the course, or by arrangement.

Sprechstunde vor/nach der Lehrveranstaltung, bzw. nach Vereinbarung.

Bachelor's projects

In case of interest in one of the proposed projects, contact us before the beginning of the 'Seminar with Bachelorarbeit'.
If the project you are interested in is not mentioned below but should be, come for a chat way before the beginning of the 'Seminar with Bachelorarbeit'.

Open:

  • Convolutional/shift-invariant dictionary learning
    Compare convolutional dictionary learning to unconstrained dictionary learning for sparse approximation and signal restoration on image or audio data,
    detailed project description to come.

  • Random subdictionaries of convolutional dictionaries
    Investigate the condition number of well separated random subdictionaries of convolutional dictionaries, in particular Gabor frames,
    detailed project description.

  • Initialisation strategies for dictionary learning
    Compare graph clustering to random initialisation for dictionary learning,
    detailed project description.

Completed:

  • Masked Hard Thresholding Pursuit for dictionary based inpainting
    D. Rotschopf
    BSc thesis, University of Innsbruck, 2020. [description]

  • Entwicklung der webbasierten Kryptografie-Anwendung KryptoKnack für die Sekundarstufe I für den Mathematikunterricht und die Digitale Grundbildung
    B. Dornauer (co-supervised with T. Hell)
    BSc thesis, University of Innsbruck, 2020. [thesis]

  • Inference acceleration for neural networks using external hardware
    L. Gutbrunner (co-supervised with M. Sandbichler)
    BSc thesis, University of Innsbruck and Besi Austria GmbH, 2019. [thesis]

  • Free the bird - Inpainting
    K. Nössing
    BSc thesis, University of Innsbruck, 2019. [description]

  • Integrating low-rank components into weighted K-SVD for dictionary based inpainting
    M. Tiefenthaler
    BSc thesis, University of Innsbruck, 2018. [thesis] [description]

  • Hard Thresholding Pursuit for Sparse Approximation
    E. Höck
    BSc thesis, University of Innsbruck, 2016. [thesis] [description]

Master's projects

We offer master's projects in the areas of signal processing, sparse approximation, dictionary learning and machine learning.
Recommended prerequisites are good knowledge of linear algebra and some interest in probability theory and/or harmonic analysis.

The goal is to contribute to an active area of research and so the project will be tailored to currently open questions and your personal interests. If you are super-strong and mega-motivated there is also the possibility to do a more substantial but paid master's thesis within the START-project 'Optimisation Principles, Models & Algorithms for Dictionary Learning', which can continue on to a PhD.

In case of interest have a look at the research or publications page and contact us for a first chat.

Nach oben scrollen