logo EDITE Hamza AGLI
Hamza AGLI
État académique
Thèse soutenue le 2017-07-20
Sujet: Raisonnement incertain pour les règles métier (URBS)
Direction de thèse:
Encadrement de thèse:
Ellipse bleue: doctorant, ellipse jaune: docteur, rectangle vert: permanent, rectangle jaune: HDR. Trait vert: encadrant de thèse, trait bleu: directeur de thèse, pointillé: jury d'évaluation à mi-parcours ou jury de thèse.
Productions scientifiques
Incremental Junction Tree Inference
International audience
Performing probabilistic inference in multi-target dynamic systems is a challenging task. When the system, its evidence and/or its targets evolve, most of the inference algorithms either recompute everything from scratch, even though incremental changes do not invalidate all the previous computations, or do not fully exploit incrementality to minimize computations. This incurs strong unnecessary overheads when the system under study is large. To alleviate this problem, we propose in this paper a new junction tree-based message-passing inference algorithm that, given a new query, minimizes computations by identifying precisely the set of messages that differ from the preceding computations. Experimental results highlight the efficiency of our approach.
IPMU16 http://hal.upmc.fr/hal-01345418 IPMU16, Jun 2016, Eindhoven, Netherlands. 2016, <10.1007/978-3-319-40596-4_28>ARRAY(0x7f0400b5bad0) 2016-06-20
Business Rules Uncertainty Management with Probabilistic Relational Models
International audience
Object-oriented Business Rules Management Systems (OO-BRMS) are a complex applications platform that provide tools for automating day-today business decisions. To allow more sophisticated and realistic decision-making, these tools must enable Business Rules (BRs) to handle uncertainties in the domain. For this purpose, several approaches have been proposed, but most of them rely on heuristic models that unfortunately have shortcomings and limitations. In this paper we present a solution allowing modern OO-BRMS to effectively integrate probabilistic reasoning for uncertainty management. This solution has a coupling approach with Probabilistic Relational Models (PRMs) and facilitates the inter-operability, hence, the separation between business and probabilistic logic. We apply our approach to an existing BRMS and discuss implications of the knowledge base dynamicity on the probabilistic inference.
RuleML16 http://hal.upmc.fr/hal-01345421 RuleML16, Jul 2016, Stony Brook, New York, United States. 2016, <10.1007/978-3-319-42019-6_4>ARRAY(0x7f03ffd85968) 2016-07-06
Thèse: Raisonnement Incertain pour les Règles Métier
Soutenance: 2017-07-20
Rapporteurs: Mathieu SERRURIER    Philippe LERAY