Workgroup Financial Mathematics
print


Breadcrumb Navigation


Content

Seminar zum Maschinellen Lernen

Dr. Jan Gairing, Prof. Dr. Thilo Meyer-Brandis


Schedule and Venue

Seminar

 

Wed 12-14

First seminar: 8th May

B 121 (QuantLab)

Seminar Description

Machine Learning has been proven extremely powerful in understanding high dimensional and non-linear phenomena. This seminar aims at introducing the students into basic models and concepts, such as

- PAC framework
- VC Dimension
- SVMs (Support Vector Machines)
- Kernel Methods
- Artificial Neural Networks
- Decision Trees
- Reinforcement Learning
- Elementary Information Geometry
- Variational Estimation


References

- Bishop. Pattern Recognition and Machine Learning (Springer, 2006)
- Mohri, Rostamizadeh, Talwalkar. Foundations of Machine Learning (2nd edition, MIT Press, 2018)
- Hastie, Tibshirani, Friedman. The Elements of Statistical Learning (2nd edition, Springer, 2009)
- Goodfellow, Bengio, Courville. Deep Learning (MIT Press, 2016)
- Amari. Information Geometry and Its Applications (Springer-Verlag, 2016)

 


For whom is this course?

Target Participants: Bachelor and master students of mathematics and Financial and Insurance mathematics.

Pre-requisites: Probability Theory. Linear Algebra. Basic knowledge in statistics.

 


Slides

The slides of the course are available here.

Additional information

  • We provide sample slides (RAR, 197KB) for Latex Beamerclass, if you are not familiar with this format you may check this tutorial.