====== Recent Advances in Deep Learning ======
\\
| [[https://ekvv.uni-bielefeld.de/kvv_publ/publ/vd?id=208846173 | 392133]] | Schönhuth | Summer 2020 | Thu 12:15-13:45 (S) in ZOOM |

==== Contents ====

In this seminar we will discuss the most recent advances and successes of Deep Learning. Therefore, we will provide a brief introduction into Deep Learning itself and then further discuss the most recent techniques and methods presented by the leading research groups of the field. Each participant will review a corresponding publication and summarize its contents in a 45 minute presentation. As a guideline see the book “Dive into Deep Learning” (https://d2l.ai/), Chapters 7 and 17.
\\
\\
The students are supposed to form groups of three, which probably leads to 5-6 groups. (a total of 20 participants are registered)
Each group should work on a scientific article and present and discuss it within a maximum of 90 minutes.

==== Groups ====

   - Nina, Francesco, Ivan (BERT; June 18)
   - Jan-Hendrik, Florian, Alexander ({{teaching:2020summer:radl:Deep_Learning___GANs.pdf|GANs}}; June 25)
   - Muhammad ({{teaching:2020summer:radl:presentation_on_gnn.pdf|GNN}}; Sep 17)
   - Sinan, Sinan, Riza ({{teaching:2020summer:radl:capsule_network.pdf|CapsNets}}; Sep 17)


==== Literature ====
  - Bidirectional Encoder Representations from Transformers (BERT)
    *  “Dive into Deep Learning”: Chapter 14 (https://d2l.ai)
    * {{teaching:literature:bert.pdf|BERT}}
  - Generative Adversarial Networks (GAN's)
    * {{teaching:literature:gans.pdf|OriginalPaper(2014)}}
    * {{teaching:literature:gans-tutorial.pdf|Tutorial (2016)}}
    * “Dive into Deep Learning”, chapter 16
  - Graph Neural Networks (GNN)
    * {{teaching:literature:benchmarking-gnns.pdf|Benchmarking Graph Neural Networks}}
    * Note the surveys
  * Surveys
    * {{teaching:literature:state-of-the-art-survey.pdf|A State-of-the-Art Survey on Deep Learning Theory and Architectures}}
    * {{teaching:literature:recent-advances-in-dl.pdf|Recent Advances in Deep Learning: An Overview}}
:!: You need to login in order to view the literature.