Programme d'échecs

Résumé

vignette|Jeu d'échecs électronique des années 1990 avec écran LCD. Un programme d'échecs est un programme informatique conçu pour jouer au jeu d'échecs. Historique Débuts et développement L'histoire des machines joueuses d'échecs n'attend pas le développement de l'électronique et de l'informatique : la première fut l'automate turc inventée en 1769 par Johan Wolfgang von Kempelen, qui joua notamment contre l'impératrice Catherine II et Napoléon Bonaparte. C'était en fait un homme de petite taille caché dans la machine. Les premiers véritables programmes virent le jour dans les années 1950, avec le développement des ordinateurs. Ils passèrent en un demi-siècle de la connaissance des règles à un niveau au moins égal à celui des meilleurs joueurs humains. Le premier programme d'échecs, Turochamp, fut écrit par Alan Turing en . Ne disposant pas d'un ordinateur assez puissant pour le faire tourner, il simule lui-même les calculs de la machine, mettant environ une de

Source officielle

https://fr.wikipedia.org/wiki/Programme_d'%C3%A9checs

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (3)

Chargement

Publications associées

Chargement

Personnes associées

Chargement

Unités associées

Chargement

Concepts associés (13)

Concepts associés

Chargement

Cours associés (2)

Cours associés

Chargement

Séances de cours associées (2)

Séances de cours associées

Chargement

Publications associées (3)

A MultiPath Network for Object Detection

Pedro Henrique Oliveira Pinheiro

The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization. The result of these modifications is that information can flow along multiple paths in our network, including through features from multiple network layers and from multiple object views. We refer to our modified classifier as a `MultiPath' network. We couple our MultiPath network with DeepMask object proposals, which are well suited for localization and small objects, and adapt our pipeline to predict segmentation masks in addition to bounding boxes. The combined system improves results over the baseline Fast R-CNN detector with Selective Search by 66 overall and by 4x on small objects. It placed second in both the COCO 2015 detection and segmentation challenges.

BMVA Press2016

Chargement

Software-Development Strategies for Parallel Computer Architectures

Wilfred Anthony Cooper

As pragmatic users of high performance supercomputers, we believe that nowadays parallel computer architectures with distributed memories are not vet mature to be used by a wide range of application engineers. A big effort should be made to bring these very promising computers closer to the users. One major flaw of massively parallel machines is that the programmer has to take care himself of the data flow which is often different on different parallel computers. To overcome this problem, we propose that data structures be standardized. The data base then can become an integrated part of the system and the data flow for a given algorithm can be easily prescribed. Fixing data structures forces the computer manufacturer to rather adapt his machine to user's demands and not, as it happens now, the user has to adapt to the innovative computer science approach of the computer manufacturer. In this paper, we present data standards chosen for our ASTRID programming platform for research scientists and engineers, as well as a plasma physics application which won the Cray Gigaflop Performance Awards 1989 and 1990 and which was successfully ported on an INTEL iPSC/2 hypercube.

1991

Chargement

This contribution introduces a hybrid GP/ES system for the evolution of chess playing computer programs. We discuss the basic system and examine its performance in comparison to pre-existing algorithms of the type alpha-beta and its improved variants. We can show that evolution is able to outperform these algorithms both in terms of efficiency and strength.

Morgan Kaufmann2002

Chargement