« Intelligence artificielle en situation réelle » : différence entre les versions


Aucun résumé des modifications
Balise : Éditeur de wikicode 2017
Ligne 10 : Ligne 10 :


== Français ==
== Français ==
IA en situation réelle
''' IA en situation réelle'''


intelligence artificielle en situation réelle
''' intelligence artificielle en situation réelle'''


système d'IA en situation réelle
''' système d'IA en situation réelle'''


système d'intelligence artificielle en situation réelle
''' système d'intelligence artificielle en situation réelle'''


== Anglais ==
== Anglais ==


=== Artificial intelligence, situated approach ===
''' Artificial intelligence, situated approach '''
 
In artificial intelligence research, the situated approach builds agents that are designed to behave effectively successfully in their environment. This requires designing AI "from the bottom-up" by focussing on the basic perceptual and motor skills required to survive. The situated approach gives a much lower priority to abstract reasoning or problem-solving skills.
In artificial intelligence research, the situated approach builds agents that are designed to behave effectively successfully in their environment. This requires designing AI "from the bottom-up" by focussing on the basic perceptual and motor skills required to survive. The situated approach gives a much lower priority to abstract reasoning or problem-solving skills.



Version du 28 avril 2019 à 08:52

Domaine

Vocabulary
Coulombe

Définition

Français

IA en situation réelle

intelligence artificielle en situation réelle

système d'IA en situation réelle

système d'intelligence artificielle en situation réelle

Anglais

Artificial intelligence, situated approach

In artificial intelligence research, the situated approach builds agents that are designed to behave effectively successfully in their environment. This requires designing AI "from the bottom-up" by focussing on the basic perceptual and motor skills required to survive. The situated approach gives a much lower priority to abstract reasoning or problem-solving skills.

The approach was originally proposed as an alternative to traditional approaches (that is, approaches popular before 1985 or so). After several decades, classical AI technologies started to face intractable issues (e.g. combinatorial explosion) when confronted with real-world modeling problems. All approaches to address these issues focus on modeling intelligences situated in an environment. They have become known as the situated approach to AI.