Integrated Lecture "Kognitive Algorithmen"

Computer programs can learn useful cognitive skills. This integrated lecture tries to communicate an intuitive understanding of elementary concepts in machine learning, their historical development and their application on real data with a special focus on methods that are simple to implement.

We will alternated a lecture and a practice session. In the practice session students will implement and apply machine learning algorithms on real data in Python.

Dates

Topics

We will cover (among other things)

• Supervised learning (linear regression techniques, linear classification, kernel based regression)
• Artificial Neural Networks (Reichardt Correlator, Perceptron Algorithm, Multilayer Neural Networks)
• Unsupervised Learning (Principal Component Analysis, Clustering)
• Model Selection

More information can be found on the ISIS Website.

Prerequisites

The following are prerequisites are helpful for taking the course:

• Basic knowledge in linear algebra and calculus
• Basic programming knowledge, programming in Python

As thematical preparation, it is recommended to visit the Python course or the mathematical foundations course which are also accreditable as optional compulsory course part and take place in the week prior to the start of the lecture period.

https://wiki.ml.tu-berlin.de/wiki/Main/WS13_PythonKurs

Credits

The integrated lecture is the compulsory part of the B.Sc. module "Kognitive Algorithmen" in Computer Science. This "Kognitive Algorihtmen" module is a 6 ECTS/SP module, and consists of

• The compulsory integrated lecture (2 SWS / 3 SP / 3 ECTS), and

• An elective (2 SWS / 3 SP / 3 ECTS): a Math refresher course, an introduction to python programming or a seminar ("Applications of Cognitive Algorithms") for a more in-depth treatment of selected applications.

The grade will be determined in a written exam at the end of the semester. The grades of the elective will not count towards the grade of the entire module.