DILS Seminar

Winter Semester 2020/21

Tuesdays, 14:15, ekvv


Corona version: Online via Zoom. Details via email.


This doctoral research seminar of the DILS graduate school is dedicated to PhD students of the Bielefeld Institute for Bioinformatics Infrastructure (BIBI) and ZB MED - Information Centre for Life Sciences. Guests are always welcome.


The topics presented are determined by the research interests of the graduate school. In general, current publications are selected, discussed and used to present the current knowledge on the research fields of interest. The main aim of this seminar is to keep the participants informed on the current developments and to critically discuss recent developments.


This semester, we follow several tracks:

  1. We jointly read the book below. Each session, we discuss a chapter. Every participant should have read the chapter and one participant is responsible for leading the discussion. We will also jointly work on the practical exercises.
    Aurélien Géron, "Hands-On Machine Learning with Scikit-Learn and TensorFlow", O'Reilly, 2019
    Online materials
  2. A participant can bring some peace of work (part of a talk, a poster, an intro of a paper, a visualization, a plot, pseudo code, etc.) which we then jointly improve/polish.
  3. A participant can prepare some current research articles on some new technology or methodology and present it in the seminar. (Each DILS student is expected to do so at least twice during their PhD.)


Date Name Topic
27.10. Everyone Topic selection, brief update on our own science
03.11. Tizian Chapter 1: “The Machine Learning Landscape”
10.11. Benedikt Chapter 2: “End-to-End Machine Learning Project”
17.11. Sebastian Chapter 2, continued
24.11. Donat Chapter 3: “Classification”
01.12. Tom Chapter 4: “Training Models”, up to (excluding) “Regularized Linear Models”, page 136
08.12. Katharina Chapter 4, continued
15.12. Janik Chapter 5: “Support Vector Machines”
22.12. Andreas Chapter 6: “Decision Trees”
29.12. –
05.01. Roland Chapter 7: “Ensemble Learning and Random Forests”
12.01. Nils Chapter 8: “Dimensionality Reduction”
19.01. Tizian Chapter 9: “Unsupervised Learning Techniques”, K-Means
26.01. Donat Chapter 9, continued: Gaussian Mixtures
02.02. Lisa Chapter 10: “Introduction to Artificial Neural Networks with Keras”
09.02. Benedikt Chapter 11: “Training Deep Neural Networks”
16.02. Tom Chapter 13: “Loading and Preprocessing Data with TensorFlow”
23.02. Katharina & Janik Chapter 14: “Deep Computer Vision Using Convolutional Neural Networks”
03.03. Presentation of our own machine learning project

Further Reading