Seminar Pattern Analysis and Machine Intelligence 2016

Reviewing the latest research in machine learning, intelligent systems, systems and software engineering. Your lecturers are Prof. Dr. Nils Bertschinger, Prof. Dr. Matthias Kaschube and Prof. Dr. Visvanathan Ramesh.

For any questions please contact us teaching@ccc.cs.uni-frankfurt.de

General

Bachelor’s students are required to give a presentation only, Master’s also need to hand in a report about their topic (~ 5-10 pages), weighting for grade 50/50. Presentations will be at least 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. You have to register with us until April, 27th. Everyone that is on our list until that date will be set for the course and given to the examination office.

TODO: Register AND select your topic until April, 27th

Dates

04.05. – Chutipong Bruhns – Perceptron

11.05. – Nicole Parrandier EM – Algorithms

18.05. – Wolfgang Stammer – Bayesian interpretation of NN

25.05. – Andy Grimm – Random Forest

01.06. – Fatime Bagheri – Self organizing maps

08.06. – Justine Smyzek – TBD

15.06. – Julian Kiling – TBD

22.06. – Rainer Killinger – Natural language processing

29.06. – Lars Petersen – Deep Learning

06.07. – Florian Stein – TBD

13.07. – Prof. Dr. Bertschinger – Neural Networks and Gaussian Processes

Topics

Classic algorithms ( Prof. Bertschinger, Prof. Kaschube )

  • MCMC
  • Gibbs sampling
  • slice sampling
  • EM algorithm
  • Variational Bayes
  • Optimization

Applications in economics and finance ( Prof. Bertschinger )

  • VAR (Vector auto regression)
  • asset pairing
  • stochastic volatility

Neural networks ( Prof. Bertschinger, Prof. Kaschube,  Prof. Ramesh )

  • Bayesian interpretations
  • Deep learning
  • Backpropagation

Vision applications / image analysis ( Prof. Ramesh )

Neural data analysis ( Prof. Kaschube )

Software plattforms (Tensor flow, Torch, Theano, Caffee, Stan etc.) ( Prof. Ramesh )

Classification ( Prof. Bertschinger, Prof. Kaschube, Prof. Ramesh )

  • Perceptron
  • Support vector machines (SVM)
  • Random forests
  • Logistic regression