Skip to Main content Skip to Navigation
Conference papers

Let the System Learn a Game: How Can FCA Optimize a Cognitive Memory Structure

Abstract : The goal of this article is to study the contribution of FCA (Formal Concepts Analysis) to (1) optimize (2) organize (3) discover new concepts or a better operation of the semantic memory of an Artificial Intelligence (AI) system based on a cognitive approach. The system has been applied to game modeling (here the Reversi board game), since games are a very good experimental field for performance evaluation. After describing the COGITO project, which tries to assess the pros and cons of cognitive modeling over pure operational but non explicative paradigms in games modeling, the paper stresses out the benefits of FCA in providing a better abstraction, and a more reliable way to handle conflictual knowledge.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00764071
Contributor : Violaine Prince-Barbier <>
Submitted on : Wednesday, December 12, 2012 - 11:45:17 AM
Last modification on : Wednesday, May 29, 2019 - 10:32:02 PM
Long-term archiving on: : Wednesday, March 13, 2013 - 3:52:44 AM

File

LNCSCogito.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00764071, version 1

Collections

Citation

William Dyce, Thibaud Marmin, Namrata Patel, Clément Sipieter, Guillaume Tisserant, et al.. Let the System Learn a Game: How Can FCA Optimize a Cognitive Memory Structure. ECAI'2012: European Conference on Artificial Intelligence, Aug 2012, Montpellier, France. pp.001-009. ⟨lirmm-00764071⟩

Share

Metrics

Record views

333

Files downloads

838