Machine Learning 6 credits

For a system to automatically recognize a face, determine the optimal time for machine maintenance, sort text documents, perform speech recognition, recognize handwritten characters, or identify patterns in large datasets – for example, identifying customer segments or different behaviors – it requires capabilities that are difficult to program explicitly. In this course, you will learn the fundamentals of how a system can acquire these capabilities by learning from data instead of being explicitly programmed. The course covers the most common algorithms for supervised and unsupervised learning, such as artificial neural networks, decision trees, and k-means clustering, which also form the basis for understanding and discussing the latest techniques in machine learning, such as deep learning.

This course is intended for professionals.

The course includes three mandatory half-day sessions.