 |
Les automates intelligents |
 |
| Jean-Paul Baquiast
Jean-Paul.Baquiast@wanadoo.fr Christophe Jacquemin christophe.jacquemin@admiroutes.asso.fr |
| |
Les automates intelligents |
|
| Jean-Paul Baquiast
Jean-Paul.Baquiast@wanadoo.fr Christophe Jacquemin christophe.jacquemin@admiroutes.asso.fr |
Revue n° 31
Retour au sommaire
Courrier
IBERAMIA'2002
CALL FOR PAPERS
14/05/02EIGHTH IBEROAMERICAN CONFERENCE ON ARTIFICIAL INTELLIGENCE
Sevilla, Spain, November 12-15, 2002
http://www.lsi.us.es/iberamia2002The 8th Ibero-American Conference on Artificial Intelligent (IBERAMIA) will take place at Seville (Spain) in november 12-15, 2002.
IBERAMIA 2002 topics include, but are not limited to:
. Intelligent User Interfaces: Multimedia Applications and Virtual Reality
. Machine Learning, Knowledge Discovery and Data Mining
. Evolutionary Computation, Genetic Algorithms and Neural Networks
. Real Time Systems
. AI Foundations and Knowledge Representation
. Knowledge Engineering (Ontologies, Knowledge Acquisition, Knowledge Representation, Reuse of Knowledge)
. Reasoning Models: Non-monotonic Reasoning, Common-Sense Reasoning, Case-Based Reasoning, Abduction, Temporal Reasoning, Belief Revision, Model-Based Reasoning, Qualitative Reasoning and Reasoning under Uncertainty
. Natural Language Processing
. Robotics, Perception and Artificial Vision
. Constraint Satisfaction, Planning and Scheduling
. Decision Support Systems
. AI in Education and Intelligent Tutoring Systems
. Multi-Agent Systems and Distributed AIIMPORTANT DATES
Papers (both tracks)
Deadline for paper submission: may 31st, 2002
Notification of acceptance: june 30th, 2002
Deadline for camera-ready papers: august 1st, 2002Workshops
Deadline for Workshop proposal: may 31st, 2002
Notification of acceptance: june 20th, 2002Tutorials
Deadline for Tutorial proposal: may 31st, 2002
Notification of acceptance: june 20th, 2002
Deadline for Tutorial hand-outs: october 27th, 2002Registration
Deadline for early registration: september 1st, 2002
Deadline for late registration: october 15th, 2002
De Salim Boudjema
saboudjema@yahoo.fr
12/05/02Bonjour. Je suis étudiant en micro robotique et je cherche de la documentation sur l'utilisation de l'algorithme genetique pour la planification
des chemin pour des robots mobiles autonomes "minirobot" " pour l'execution d'une tache "BOUDJEMA: résidence universitaire Fourier bat F2 cham 001
19, chemin de l'épitaphe 25005 BESANCON cedex FRANCE
De William Guyot
Wguyot@wanadoo.fr
10/05/02Je connais bien votre site et tient en grande estime sa clarté, son esprit humaniste et sa prodigalité digeste.
Je travaille actuellement à la rédaction d'un article sur la modification du geste technique du chirurgien relativement au changement contextuel impliqué par la "station robotique" au sein de la salle d'opération. Je vous en ferais part dès que celui-ci sera achevé.
De Bruce Edmonds
Journal of Mimetics
08/05/02Cultural Transmission and the Capacity to Approve or Disapprove of Offspring's Behaviour
by Laureano Castro and Miguel A. ToroAbstract.
We suggest that human cultural learning was made possible by the simultaneous appearance, in one of our hominid ancestors, of two capacities: the capacity to imitate others' behaviour and the capacity to approve or disapprove of others' behaviour. With the help of a mathematical model, we have studied the conditions that allow the evolution of both capacities. We consider four different genotypes: "the only-learner" that learns by trial and error, "the imitator" that learns by trial and error and imitation, "the only-assessor" that learns by trial and error but that can also approve or disapprove of offspring's behaviour and, finally, "the assessor", who behaves like the imitator but, he can approve or disapprove of offspring's behaviour. The assessor genotype is the best genotype and the only-learner genotype is the worst when the learned behaviour that would be culturally transmitted is adaptive. If this behaviour is maladaptive, the genotype only-assessor is the best genotype and the genotype assessor can be the worst genotype. Notwithstanding, in this situation, the assessor can also be better than the imitator and even better than the only-learner. The success of assessor is due to his capacity to increase the phenotypic correlation between parents and offspring, and thus speeding the rate at which natural selection, if present, will increase or decrease the frequency of learned behaviours.
Available at http://jom-emit.cfpm.org/2002/vol6/castro_l&toro_ma.html
Voir aussi Meeting Report: Engineering and Physical Sciences Research Council Network on Evolvability in Biology and Software Systems Symposium on Software Evolution and Evolutionary Computation, University of Hertfordshire, UK 7th - 8th February 2002 http://jom-emit.cfpm.org/2002/vol6/gatherer_d_report.html