NMTS

Name:

Neural methods for technical systems
Neural methods for technical systems

Event type:

Lecture

Content:

The aim of the course is to teach the fundamentals of data processing based on neural networks and their use for various technical applications such as signal processing, diagnosis, modeling and control.

• Historical development, the simplest processing unit: the neuron.
• Architectures of neural networks:
  • Hopfield models;
  • simple perceptrons;
  • multi-layer perceptrons;
  • dynamic networks.
• Learning methods:
  • Delta-rule,
  • Backpropagation,
  • variants of backpropagation,
  • Newton and Levenberg-Marquardt learning methods.
• Applications:
  • Pattern recognition,
  • function approximation.

Target audience:

Students in the 1st and 2nd level of study from the 5th semester onwards.

Scope:

2 SWS lecture, 1 SWS exercise, 4 CP

Dates:

The lecture takes place in the summer semester.

Documents:

Announcement in the lecture

Certificate of achievement:

Written exam

Lecturer:

• Dr.-Ing. Mohamed Ayeb