d e f es 
AICOS News
15.03.2020
Coronavirus: continuation of our activities
Independently of the coronavirus epidemic... 
more Linie
20.02.2020
AICOS Technologies at PCH Meetings 2020 in Lyon
Lyon - 25.-26.11.2020: International business... 
more Linie
05.01.2020
Our training schedule for spring / summer 2020 is on-line!
You want to deepen your knowledge in data... 
more Linie
Search
Go
Courses

Neural Networks and Genetic Algorithms in Practice

Please contact

Neural networks have the capability of "learning" complex relationships between given data even in the case where statistical methods are of limited applicability. In this training session, the basic ideas of neural networks - which have found various practical applications - will be discussed. In addition, genetic algorithms are presented, which are used in the learning process of neural networks.


What would you learn ?
Are you in possession of large and complex data sets, containing valuable hidden information? Do you want to get reliable predictions based on historical data? Or do you have to find out optimal settings for certain input parameters of a system? In that case, neural networks and genetic algorithms might be able to help you. Neural networks have the capability of "learning" complex relationships between given data even in the case where classical statistical methods are of limited applicability. In this course, the basic ideas of neural networks - which have found various applications (e. g. in chemical industry, robotics, forecasting of share courses and exchange rates, pattern recognition, medicine, etc.) will be discussed. In addition, genetic algorithms are presented, which are a very robust all-purpose optimization method. Genetic algorithms are applied to the learning process of neural networks and for the optimization of input parameters. The methods and their application are explained using practical examples; there will be software demonstrations on the PC.

Who should attend ?
  • For managers and scientists
  • A minimal knowledge of mathematics is recommended but not necessary

Which topics are covered ?
 Neural Networks
 History
Feed-forward networks
Learning process with data (backpropagation)
Advantages and disadvantages of neural networks
Case study
 Genetic Algorithms
 Biological motivation
Basic terms: fitness, selection, recombination, mutation
Advantages and disadvantages
Application examples
 Software
 Comparison of software solutions from different vendors for neural networks
Demonstration and exercise with Excel


Any questions ?
powered by Swisscom AG
c