Artificial Intelligence (AI) and Machine Learning (ML) have become practically indispensable in today’s IT world. Indeed, they hold enormous potential. However, following the hype, there are often unrealistic or unfounded expectations projected onto these new “magic technologies”. Practice, on the other hand, shows more of craftsmanship, statistical principles, and trial-and-error methodology.

Everyone who wants to explore potential applications of machine learning for their own projects and have a more informed opinion on the subject in general will gain a comprehensive overview of the basics, but also the limits, of artificial intelligence in this three-day course. It offers an ideal opportunity to get hands-on with small but impressive AI examples and develop a feeling for the underlying principles of machine learning.


Own (simple) programming exercises in Python are variedly supported by (little) theory, demonstrations, hands-on experiments, discussions, and several aha experiences. All three days will be enriched with clear introductions of terms, application examples, exciting episodes, and impressive demonstrations, also outside the Python context.

  • Day 1 | Data Science: Data Preparation with NumPy, pandas, and Matplotlib
    • NumPy arrays vs. Python data structures
    • (vector) functions on NumPy arrays
    • heterogeneous data structures in pandas
    • input and output of several file formats
    • visualizations using different diagram types in Matplotlib
  • Day 2 | Machine Learning: Classical Statistical Methods with scikit-learn
    • basic principles and classes of machine learning methods
    • challenges of machine learning in practice
    • supervised learning:
      • classification
      • regression
      • support vector machines (SVMs)
      • decision trees
    • unsupervised learning:
      • clustering
      • anomaly detection
    • short insides into:
      • semisupervised learning
      • reinforcement learning
  • Day 3 | Deep Learning: Artificial Neural Networks with Keras and TensorFlow
    • basic functionality of (artificial) neural networks
    • structure of and relationship between Keras and TensorFlow
    • deep learning models and layers
    • computer vision with convolutional neural networks (CNNs)
    • challenges and weaknesses of deep learning

Course Objectives

Answers to many fundamental questions:

  • How are “artificial intelligence” and “machine learning” related?
  • What types of machine learning algorithms do exist, and how do they work at their basic level?
  • How can data preparation, classical statistical methods, and artificial neural networks be implemented in Python?
  • Why are the quality and quantity of training data so essential?
  • Where can AI solutions realistically be applied in the future and at what expense?

Target Groups

  • Individuals from the software field with initial programming experience (preferably in Python), who would like to take their first steps in the field of machine learning and obtain an overview.


Christian Heitzmann is a Java-, Python- and Spring-certified software developer with a CAS in Machine Learning and owner of SimplexaCode in Lucerne. He has been developing software for over 20 years and has been teaching and lecturing for 12 years in the areas of Java and Python programming, mathematics, and algorithms, among others. He regularly writes articles for IT journals.

Shortlink to this page: