Login |
 
 

Overview

Credits: 3 SWS 3, 5 Credits

Course type : Lecture

Language: english

Lecture: Mo, 15:15 - 16:45, R512 (weekly)

Exercises:

Tue, 13:30 - 15:00, M1101 (biweekly, 02.05., 16.05., 30.05. etc.)

Thu, 15:15 - 16:45, D247 (biweekly, 04.05., 18.05., 01.06. etc.)

Slides etc.

More information concerning this lecture, including material and exercises, can be found on the following websites:

English

German

Description

Contents:

  • Biological background
  • Threshold logic units and their geometric interpretation
  • General neural networks
  • Multilayer perceptrons
  • Deep learning
  • Radial basis function networks
  • Learning vector quantization and self-organizing maps
  • Hopfield networks and associative memory
  • Recurrent neural networks

Learning Objectives:

  • Knowledge of the most common types of artificial neural networks
  • Suitability of different network types for supervised and unsupervised learning tasks
  • Understanding of the advantages and disadvantages of the different types of neural networks depending on the structure of the data
  • Training neural networks with gradient descent and its variants
  • Ability to select a neural network type for a given problemApplication of training artificial neural networks in practice

Important

Registration via StudIS required.