Seminar Pattern Analysis and Machine Intelligence (Winter Semester 2017)
Reviewing the latest research in machine learning and intelligent systems. Your lecturers are Prof. Dr. Nils Bertschinger, Prof. Dr. Matthias Kaschube and Prof. Dr. Visvanathan Ramesh.
Time: Thursday, 8:00 am c.t. SR 9
For any questions please contact us teaching@ccc.cs.uni-frankfurt.de
General
Bachelors students are required to give a presentation only, Masters also need to hand in a report about their topic (~ 5-10 pages), weighting for grade 50/50. Presentations will be around 30 minutes plus discussion with the class. Course language is English. We will meet every week and presence is mandatory. Either choose one of the topics below and search for literature for yourself (papers, book-chapters, etc.), or choose a paper from here or request one from any professor above. Registration is mandatory and will be passed to the examination-office.
Presentation Dates and Schedule
- 19.10.2017 – Seminar Overview, Logistics, Themes of Papers
- 26.10.2017 – no seminar, paper selection and review
Seminar Schedule:
Datum | Betreuer | anrede | vorname | nachname | Thema |
11/16/2017 | Ramesh | Herr | Felix | Schatten | On the Origin of Deep Learning |
11/16/17 | Ramesh | Herr | Sebastian | Voinea | On the Origin of Deep Learning |
11/23/17 | Ramesh | Frau | Madeleine | Henkel | 50 years of Data Science |
11/23/17 | Ramesh | Herr | Philipp | Scholl | 50 years of Data Science |
12/7/17 | Bertschinger | Herr | Andreas | Haupt | Deep Symmetry Networks |
12/7/17 | Bertschinger | Herr | Arvin | Matic | On Random Weights and Unsupervised Feature Learning |
11/30/17 | Bertschinger | Frau | Yana | Ezhkina | Bayesian analysis of GARCH and stochastic volatility: modeling leverage, jumps and heavy-tails for financial time series |
12/14/17 | Bertschinger | Herr | Boris | Hähnlein | Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift |
12/14/17 | Bertschinger | Herr | Fabian | Knöller | Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images |
12/21/17 | Bertschinger | Frau | Katarzyna | Kujawa | Model-based machine learning |
12/21/17 | Bertschinger | Herr | Nikias | Heß | Stan: A probabilistic programming language for Bayesian inference and Optimization |
1/11/18 | Ramesh | Herr | Moritz | Faust | On Cognitive Dynamic Systems: Cognitive Neuroscience and Engineering Learning From Each Other |
1/18/18 | Kaschube | Herr | Christopher | Posselt | Deep convolutional models improve predictions of macaque V1 responses to natural images |
1/18/18 | Kaschube | Herr | Eike | Henrich | Deep convolutional models improve predictions of macaque V1 responses to natural images |
1/25/18 | Kaschube | Herr | Bashir | Lawand | Synthesising Dynamic Textures using Convolutional Neural Networks |
1/25/18 | Kaschube | Herr | Julius | Taylor | Texture Synthesis using Convolutional Neural Networks |
2/1/18 | Kaschube/Ramesh | Frau | Yu Yi | Yang | Representation learning |
2/1/18 | Kaschube/Ramesh | Herr | Sitong | Yu | A Taxonomy of Deep Convolutional Neural Nets for Computer Vision |
Topics and Papers:
Link to Papers from Prof. Ramesh (password protected, password will be sent by email to registrants)