Je suis d'accord avec toi, il y a en gros deux variables: la rapidité de calcul et la fonction d'évaluation de la position des pièces.
Pour la première variable Deep Blue avait des circuits spécialisés. Selon l'article Wikipédia : "The system derived its playing strength mainly out of brute force computing power. It was capable of evaluating 200 million positions per second".
Pour la fonction d"évaluation c'est en gros une bibliothèque des parties déjà jouées par les maîtres du jeu d'échecs:
"Deep Blue's evaluation function was initially written in a generalized form, with many to-be-determined parameters (e.g. how important is a safe king position compared to a space advantage in the center, etc.). The optimal values for these parameters were then determined by the system itself, by analyzing thousands of master games. The evaluation function had been split into 8,000 parts, many of them designed for special positions. In the opening book there were over 4,000 positions and 700,000 grandmaster games. The endgame database contained many six piece endgames and five or fewer piece positions. Before the second match, the chess knowledge of the program was fine tuned by grandmaster Joel Benjamin.
Tout ça a l'air quand même bien plus calculatoire que le traitement du langage naturel non ?
[^] # Re: Pas d'accord !
Posté par patrick_g (site web personnel) . En réponse au journal Watson, Jeopardy et le test de Turing. Évalué à 7.
Pour la première variable Deep Blue avait des circuits spécialisés. Selon l'article Wikipédia : "The system derived its playing strength mainly out of brute force computing power. It was capable of evaluating 200 million positions per second".
Pour la fonction d"évaluation c'est en gros une bibliothèque des parties déjà jouées par les maîtres du jeu d'échecs:
"Deep Blue's evaluation function was initially written in a generalized form, with many to-be-determined parameters (e.g. how important is a safe king position compared to a space advantage in the center, etc.). The optimal values for these parameters were then determined by the system itself, by analyzing thousands of master games. The evaluation function had been split into 8,000 parts, many of them designed for special positions. In the opening book there were over 4,000 positions and 700,000 grandmaster games. The endgame database contained many six piece endgames and five or fewer piece positions. Before the second match, the chess knowledge of the program was fine tuned by grandmaster Joel Benjamin.
Tout ça a l'air quand même bien plus calculatoire que le traitement du langage naturel non ?