This course provides a hands-on introduction to modern machine learning for students with Python skills but no prior machine learning experience. It covers all the tools, techniques, and processes necessary to successfully run simple machine learning projects and provides a solid foundation for moving into more advanced topics.

While the course provides an overview of different approaches, we will focus on two techniques for solving ML problems that have not only proven themselves by winning numerous competitions on websites such as Kaggle, but have also been successfully used in countless industry projects: ensembles of decision trees and deep lear

Before any ML technique can be applied to a problem, it is necessary to analyze, clean, visualize, and transform the existing data. The first part of the course will deal with these less glamorous but absolutely important aspects of ML projects. In the second half, we will use decision trees and pre-trained deep networks to develop solutions with state-of-the-art performance for various ML problems.

What do you learn on the first day?

We begin with an ML introduction. In this short section we cover questions such as: What is ML? Which problems can be solved with ML techniques, which are less suitable? What does an ML development project look like? What best practices should you apply?

In many cases, the success of practical machine learning projects depends more on the quality of the data used to drive the algorithms than on the details of the ML algorithm. In this section, we cover the most important tools for collecting, cleaning, analyzing, and preparing data in Python.

What do you learn on the second day?

On the second day, you will learn Traditional Machine Learning. While Deep Learning is a major focus in academic research and provides superior results for most perceptual problems, traditional ML techniques are still viable solutions to many problems and are often used as baselines against which more elaborate solutions are evaluated.

What do you learn on the third day?

CERTIFICATE

Of course, as a participant in the Machine Learning course for Python programmers you will receive a certificate. Prerequisite for this is the complete participation in all course units and programming tasks and the successful programming of a small final project. However, after this intensive machine learning training you will have more fun than stress.

The agenda is written in English due to the numerous technical terms. Descriptions as well as course material will be provided in German. You can book the course either in German or English.

All seminar contents are individually adapted to the wishes of our participants. They can vary depending on the level of knowledge and will be defined together with the seminar leader on day 1. In this Machine Learning with Python seminar you have the choice of the following topics:

Deep Learning (PyTorch)

In this part of the course we will look at deep learning and in particular how pretrained DL models can provide us with state-of-the-art quality solutions even in cases where we have limited data or computational budget.

• What is deep Learning?
• Advantages and disadvantages
• Basics of deep learning
• Fully-connected networks
• multi-layer perceptrons
• Deep learning for image classification
• CNNs, pretrained models
• Introduction to natural language understanding
• using pertained transformers

Moving ML Project into Production

There are many possibilities for errors when moving ML models from training to production. While the topic is too large to treat in detail in this course, we give at least an overview of some of the most important concerns when moving small-scale projects to production.

• Saving and loading models
• Ensuring consistency between training and production
• Monitoring model performance and updating production models