Software Packages
I have developed the following software packages:
SplineOmics
Overview
An R package for finding significant features (hits) in time-series -omics data using splines and limma for hypothesis testing. It clusters hits based on spline shape and generates summary HTML reports.
Honors and Awards
Welcome to the honors and awards section of my portfolio. Here, I list achievements like grants, fellowships, scholarships, etc.
DOC Fund of the Austrian Academy of Sciences (ÖAW)
I received a DOC Fellowship from the Austrian Academy of Sciences (ÖAW), a highly competitive grant supporting outstanding PhD students across all research disciplines. The fellowship is awarded based on academic performance, research potential, and project quality. I secured €147,240 in total funding, with €49,080 allocated for my personal research support over three years, based on my independently proposed research project.
Self Written Data Science Ebooks
I have authored the following ebooks:
Navigating Machine Learning Projects
Overview
On the internet, there are lots of different resources explaining HOW different
things in machine learning work, such as the technical details of neural
networks. However, resources about how to navigate machine learning projects
are much rarer. Few people discuss WHEN to for example apply neural networks,
or what to do when your choosen model does not perform well enough. This is
the gap I wanted to fill with this ebook. It gives you an overview of
different techniques, methods, models, etc. that exist, and tells you when to
use them. This can be considered as the art of machine learning, since it is
mostly based on experience of successful practitioners, such as Andrew Ng,
Andriy Burkov, and others. In this book, I compiled the experience from
those people that they shared over their books or online courses.
Organising Machine Learning Projects
Overview
A guide on how to organise machine learning projects, covering environment
and dependency management, best practices for Git commits, documentation in
ML projects, experiment logging and tracking, dataset versioning, and model
storage and versioning. I think many of the things written down in the book
seem obvious and clear, but I know from experience that many projects in the
end still fall short on several of those things. Therefore, I think it is
very useful to have those strategies and best practices written down, to
revise them regularly and allow for sharing with team members to standardize
the organisation and documentation within a project.