Artificial Intelligence and Machine Learning for Connected Systems

The Description of the module you find here.

 

The course alternates between theoretical lectures and lab sessions. The main idea consists of presenting the theoretical background of a specific subject, followed by a lab session in which students will learn more details about each model and algorithm with practical examples using the most popular tools and libraries available. The course includes hands-on lab sessions with practical assignments, some of which are evaluated. The course is connected-systems oriented, which means that, in addition to the most popular datasets, like MNIST and California houses, students will also see other examples of network-related datasets.

Topics:

• Introduction to AIML.
• Practical skills and Linear Regression.
  Lab: end-to-end work, exploratory data analysis.
• Supervised Learning and Classification (Decision Trees and Random Forest, Bayesian Detection, Non-Parametric Classifiers)
  Lab: Classification, Linear and Quadratic Discriminants, K-nearest neighbors (KNN).
• Dimensionality Reduction
  Lab: Principal Component Analysis (PCA), Multiple Discriminant Analysis (MDA)
• Unsupervised Learning
  Lab: Clustering
• Artificial Neural Networks, Deep Neural Networks (DNN)
  Lab: Neural Networks, Multi-Layer Perceptron (MLP)
• Training enhancement techniques (e.g. Ensembles, in DNN)

Complementary content:

• Basics on Reinforcement Learning
  Lab: Basics of Reinforcement Learning
• Data processing tools (e.g. TensorFlow, Scikit learning)

Lab: management of time-series in Recurrent Neural Networks (RNN) 

Lab tools

• Language: Python
• Frameworks and libraries: Numpy, Pandas, Matplotlib, Scikit-Learn, Tensor Flow, Keras, Google Colab, LATEX, and Overleaf 

Datasets

• Iris
• Ridership: Bus and Rail rides in Chicago
• CTU-13: 13 attack scenarios from botnets
• 5G-Traffic: Traffic load in different cities in France
• LiveStreaming: Live streaming data of user’s connections (World Cup matches).
  
   

Online-learning takes place as self-study units as well as group work. For structuring the self-study-part there are provided videos that illustrate the contents and an elaborated script. The script is developed especially for students that work full-time while studying, according to the didactic concept of Ulm University. The script contains learning stopps, multiple and single choice tests, quizzes, exercises, etc.

Your mentor will offer online seminars in periodic intervals. These seminars will help you handling the exercises and working on the learning matters. An online forum for exchange with the other students will also be available. 

• An academic degree is required.
• Calculus, Algebra, basic concepts of statistics and probability. Prior knowledge on Python is strongly recommended.

After finishing your exam successfully you will get a certificate and a supplement, which will list the contents of the module and the competencies you have acquired. The supplement confirms you the equivalent of 3-7 credit points (ECTS).