Frequently asked questions
In the following some questions and answers are listed, with which we are confronted repeatedly in our daily work.
Questions about the technology
- Artificial Neural Networks are Blackbox routines. Are you allowed to use them?
- What's so special about Artificial Neural Networks?
- How many data do you need for training an Artificial Neural Network?
- How to safeguard Artificial Neural Networks against unexpected extrapolation behaviour?
- Artificial Intelligence, Computational Intelligence, SoftComputing, Natural Computation - what's the difference?
- What's the difference between Machine Learning, Artificial Neural Networks, and Deep Learning?
- Why is adaptivity so important?
- Nowadays nearly everything is called "intelligent". What's so special about it then?
- Monte Carlo - isn't that quite expensive?
- Optimization does not work, what can be done?
- Despite having excellent optimization results the real system fails totally – what went wrong?
- Why is such a fuss made about the “requirements”?
- What does "robustness management" mean?
- What does "complexity management" mean?
- And what's so special about ANDATA's approach?
- This all sounds very abstract and scientific, can't it be described more simply and intuitively?
- How can a company in the size of ANDATA deal with such a broad spectrum of applications?
- What's the Difference between Autonomous, Automated, Connected, and Cooperative Driving?
- What are the requirements to run ANDATA software?
- Is it manadory to have a MATLAB license for the ANDATA software tools?
- Which licensing options are available for the software?
- What's behind the App- and Toolbox-Concept of the ANDATA software?
- How to install the ANDATA software?
- Why MATLAB and not Python, R, Tensorflow, or similar open and free software?