Machine Learning in Information and Communication Technology (ICT) – lecture
Course No: 18-kp-2110-vl
Instructors: Prof. A. Klein, Prof. A. Zoubir, Prof. M. Pesavento, Prof. H. Köppl
Contents: Introduction into machine learning from the perspective of an engineer.
Most important models and learning procedures will be presented and explained by problems in information and communication systems.
Kevin P. Murphy: Machine Learning – A probabilistic perspective, MIT Press, 2012
Christopher M. Bishop: Pattern recognition and Machine Learning, Springer, 2006
Peter Bühlmann und Sara van de Geer: Statistics of high-dimensional data – Methods, theory and applications, Springer, 2011
Machine Learning in Information and Communication Technologies – exercise
Course No: 18-kp-2110-ue
The module provides an introduction to the emerging field of machine learning from an engineering perspective. Important models and learning methods are presented and exemplified through problems from information and communication technology.
- Fundamentals of probability theory and multivariate statistics
-Taxonomy of machine learning problems and models (supervised, unsupervised, generative, discriminative)
- Probabilistic graphical models: categories, inference and parameter estimation, structure learning, probabilistic programming
- Hidden Markov models (HMM): Theory, Algorithms and ICT applications (e.g. Viterbi decoding of convolutional codes)
- Fundamentals of Bayesian inference, Monte Carlo methods, Bayesian non-parametrics
- Regression and classification: theory, methods and ICT applications
- Dimensionality reduction, clustering and big data analytics: methods and application in communications and signal processing
- Approximate algorithms for scalable Bayesian inference; application in signal processing and information theory (e.g. decoding of LDPC codes)
- Inference as optimization, variational inference
- Deep neural networks (deep learning): Models, learning algorithms, libraries and ICT applications
Machine Learning in ICT – practical training
Course No: 18-kp-2110-pr
If you are interested in this course, you are kindly invited to contact us for more information and to fix a time period for your individual practical training.
Computational Modeling for the IGEM Competition
Course No: 18-kp-2100-se
If you are interested in this course, you are kindly invited to contact us for more information and to fix a time period for your individual IGEM seminar.
Course No: 18-kp-1000-ps Proseminar ETiT
You can register for a proseminar at BCS at any time.
If you are interested in doing a proseminar under supervision of BCS, please, do not hesitate to contact any member of BCS and ask for details.
Contents: Read published books or papers on a given subject in Electrical Engineering and Information Technology. Write a summary and present it using multi media technology.
Project seminar Communication and Sensor Systems
Course No: 18-kp-1041-pj
Investigating and solving specific problems concerning communication and sensor systems (Problems concerning communications engineering, microwave technology, signal processing, sensor networks etc. are possible, topics will be defined out of the recent research topics of the involved labs), working on a a given task by one’s own, organizing and structuring of a seminar task, searching and analyzing of scientific reference publications for a given task, summarizing achieved results and conclusions by means of a written report, presenting achieved results and conclusions and defending them in an oral discussion including audience.
Telecommunications – seminar
Course No: 18-kl-9010-se
In this seminar students working on Bachelor thesis, Master thesis, Studienarbeit and Diplomarbeit, research assistants of the institute and guest researchers present their work. The presentation topics are indicated by announcement.
All students interested in, or currently working on a thesis in the field of communication technology are encouraged to participate in this seminar.
Introduction to Scientific Computing with Phyton
Course No: 18-st-2070-pr
Scientific computing is introduced via six case studies. Exemplary engineering problems that are know from basic engineering courses are solved on a computer using fundamental methods from numerical mathematics. Opportunities and limitations of this approach are highlighted.
The required material on numerical mathematics is taught via preparatory scripts for each case study. During the practical exercises the methods are implemented in the current computing environment Python under the guidance of suitable teaching personnel.
The case studies cover the following numerical topics:
- Formulation and solution of systems of linear equations, sparse methods
- Integration of ordinary differential equations (ODE) and their analysis based on eigenvalues
- Mathematical optimization and automated differentiation
- Linear regression and approximation, first Machine Learning algorithms
- Discretization of simple partial differential equations (PDE)