NMTS

Name:

Neural methods for technical systems
Neural methods for technical systems

Type of course:

Lecture

Content:

• Introduction:

  Biological model, historical development, areas of application

• The Hopfield model

  The basic problem, The model, The single-pattern problem, The multi-pattern problem, Analysis of convergence and capacity properties

• Multi-layer perceptrons:

  Simple perceptrons, threshold units, linear-separable problems, linear units, gradient method, delta rule, nonlinear units

  Multi-layer networks MLP, approximation capabilities and existence theorem, inference, open points, cost function, local minima, learning data, network structure, generalization capability, overfitting problem, backpropagation, variants of the backpropagation method, Newton method

• Dynamic neural networks:

  Time Delayed Neural Networks TDNN, Recurrent Neural Networks RNN

• Radial basis function networks

Target group:

• 1st and 2nd level students from 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

Proof of performance:

• Written exam

Lecturer:

• Dr.-Ing. Mohamed Ayeb

Back to overview