7. Stability and safety
One of the problems of artificial neural network technology is to verify stability and, to further refine the practitioner's formulation, to verify reliability and consistency of behavior. This difficulty arises not only in the case of neural networks, but also in that of many adaptive control circuits (e.g. learning control loops).
Stability and safety are essential in practice.
A typical application of artificial neural networks in control is to improve a known existing conventional process. It is rare to completely replace conventional processes, or to break new ground.
The purpose of installing an artificial neural network is to take advantage of the learning possibilities and ease of model building and control, which conventional processes can only achieve inadequately or at the cost of costly effort. This is...
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
Stability and safety
Acceptance and use
Article included in this offer
"Control and systems engineering"
(
143 articles
)
Updated and enriched with articles validated by our scientific committees
A set of exclusive tools to complement the resources
References
Articles available on the Web
- (1) - YASMINE (Y.) - Stage sur les réseaux de neurones. - CICT, 1999. http://www.cict.fr .
- (2) - HARDY (J.-M.), STRASSERA (A.) - Les réseaux de neurones....
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed? Log in!
![Écoutez notre podcast Cogitons Sciences : Intégrer l’IA dans votre entreprise, pour un usage utile et raisonné [L’IA s’invite dans nos métiers #2]](https://www.techniques-ingenieur.fr/actualite/wp-content/uploads/2024/01/CS-IA-ep2.png)
![Écoutez notre podcast Cogitons Sciences : Comment l’IA révolutionne notre façon de travailler ? [L’IA s’invite dans nos métiers #1]](https://www.techniques-ingenieur.fr/actualite/wp-content/uploads/2024/01/IA-ep1.png)
