Si vous utilisez un lecteur d'écran, cliquez ici pour désactiver la recherche instantanée Google.
Connexion
×

Vous venez ici souvent ? Faites de Google votre page d'accueil.

OK

Google

La recherche instantanée Google n'est pas disponible. Appuyez sur Entrée pour lancer la recherche. En savoir plus
La recherche instantanée Google a été désactivée, car votre connexion est trop lente. Pensez à appuyez sur Entrée pour lancer la recherche.
Appuyez sur Entrée pour lancer la recherche.
Tous
Actualités
Images
Vidéos
Shopping
PlusOutils de recherche
    • Paramètres de recherche
    • Langues (Languages)
    • Activer SafeSearch
    • Recherche avancée
    • Historique
    • Aide sur la recherche
Environ 883 résultats (0,89 secondes) 
Looking for results in English?
Change to English
Continuer en Français
Paramètres de langue
Rappel concernant les règles de confidentialité de Google
Me le rappeler plus tard
Consulter

 
 

Résultats de recherche

Deep Learning Games - Google Research

research.google.com/pubs/pub45550.html
  1. En cache
Traduire cette page
Dale Schuurmans, Martin Zinkevich. BibTeX. @inproceedings{45550, title = {Deep Learning Games}, author = {Dale Schuurmans and Martin Zinkevich}, year ...

NIPS 2016 Accepted Papers

https://nips.cc/Conferences/2016/AcceptedPapers
  1. En cache
Traduire cette page
Deep Learning Games Dale Schuurmans*, ; Martin Zinkevich, Google; Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear ...

Research at Google

https://research.google.com/
  1. En cache
  2. Pages similaires
Traduire cette page
Deep Learning Games. Dale Schuurmans, Martin Zinkevich. NIPS 2016 (2016) (to appear) ... NIPS 2015 and Machine Learning Research at Google ...

[PDF]A Portable Deep Learning Model for Modern Gaming AI

cs231n.stanford.edu/reports2016/113_Report.pdf
  1. En cache
Traduire cette page
The Game Imitation: A Portable Deep Learning Model for Modern Gaming AI. Zhao Chen. Department of Physics. Stanford University, Stanford, CA 94305.

[PDF]Deep Online Convex Optimization with Gated Games - arXiv.org

https://arxiv.org/pdf/1604.01952
  1. En cache
Traduire cette page
de D Balduzzi - ‎2016 - ‎Autres articles
7 avr. 2016 - Deep learning algorithms have yielded impressive perfor- mance across a range of ... reformulate learning in convnets as gated games and adapt results on ...... [65] O. Aslan, X. Zhang, and D. Schuurmans, “Convex Deep Learning via ... [84] M. Zinkevich, “Online Convex Programming and Generalized In-.

Deep Learning for Reward Design to Improve Monte Carlo Tree ...

arxiv.org › cs
  1. En cache
Traduire cette page
de X Guo - ‎2016 - ‎Autres articles
24 avr. 2016 - ... for Reward Design to Improve Monte Carlo Tree Search in ATARI Games ... Combining PGRD and Deep Learning in this way should make ...

XML (NLM) - Frontiers

journal.frontiersin.org/article/10.3389/frobt.2015.00039/xml/nlm
  1. En cache
The backbone of almost all deep learning algorithms is backpropagation, ... distributions. deep learning representation learning optimization game ... performance guarantees in the stochastic and adversarial settings (Zinkevich, ...... Y. Schuurmans D. Lafferty J. D. Williams C. K. I. Culotta A. ( Curran Associates, Inc. ), 1 – 9 .

An Introduction to Counterfactual Regret Minimization

modelai.gettysburg.edu/2013/cfr/
  1. En cache
  2. Pages similaires
Traduire cette page
In 2000, Hart and Mas-Colell introduced the important game-theoretic algorithm of ... to Counterfactual Regret Minimization - Learn the game-theoretic regret-based ... a deep experiential knowledge of game-theoretic regret-based algorithms that leaves ... Regret Minimization, through Section 2 [Optional: M. Zinkevich et al.

Grammars for Games: A Gradient-Based, Game-Theoretic Framework ...

https://www.researchgate.net/.../291186593_Grammars_for_Games_A_Gra...
Official Full-Text Publication: Grammars for Games: A Gradient-Based, ... The backbone of almost all deep learning algorithms is backpropagation, which is simply a gradient computation distributed over a neural network. ...... eds D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou (Curran Associates, .... Zinkevich, M. (2003).

Learning Deep Architectures for AI - ACM Digital Library

dl.acm.org/citation.cfm?id=1658424
  1. Pages similaires
Traduire cette page
de Y Bengio - ‎2009 - ‎Cité 2767 fois - ‎Autres articles
Foundations and Trends® in Machine Learning archive .... Processing Systems 21 (NIPS'08), (D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, eds.) ...... M. Zinkevich, "Online convex programming and generalized infinitesimal gradient ..... Deep learning for real-time Atari game play using offline Monte-Carlo tree search ...

1234567Suivant
 - En savoir plus   
Aide Envoyer des commentaires Confidentialité Conditions Utiliser Google.com
  • Mon compte
  • Recherche
  • Maps
  • YouTube
  • Play
  • Actualités
  • Gmail
  • Drive
  • Agenda
  • Google+
  • Traduction
  • Photos
Plus
  • Shopping
  • Docs
  • Livres
  • Blogger
  • Contacts
  • Hangouts
Autres résultats Google