A totally subjective multifactorial choice procedure
A variant of gravitational classification
In this article there is proposed a new two-parametrical variant of the gravitational classification method. We use the general idea of objects' behavior in a gravity field. Classification depends on a test object's motion in a gravity field of training points. To solve this motion problem, we use a simulation method. This classifier is compared to the 1NN method, because our method tends towards it for some parameter values. Experimental results on different data sets demonstrate an improvement...
A viscosity solution method for Shape-From-Shading without image boundary data
In this paper we propose a solution of the Lambertian shape-from-shading (SFS) problem by designing a new mathematical framework based on the notion of viscosity solution. The power of our approach is twofolds: (1) it defines a notion of weak solutions (in the viscosity sense) which does not necessarily require boundary data. Moreover, it allows to characterize the viscosity solutions by their “minimums”; and (2) it unifies the works of [Rouy and Tourin, SIAM J. Numer. Anal.29 (1992) 867–884],...
About the choice of the variable to unassign in a decision repair algorithm
The decision repair algorithm (Jussien and Lhomme, Artificial Intelligence 139 (2002) 21–45), which has been designed to solve constraint satisfaction problems (CSP), can be seen, either (i) as an extension of the classical depth first tree search algorithm with the introduction of a free choice of the variable to which to backtrack in case of inconsistency, or (ii) as a local search algorithm in the space of the partial consistent variable assignments. or (iii) as a hybridisation between local...
About the choice of the variable to unassign in a decision repair algorithm
The decision repair algorithm (Jussien and Lhomme, Artificial Intelligence139 (2002) 21–45), which has been designed to solve constraint satisfaction problems (CSP), can be seen, either (i) as an extension of the classical depth first tree search algorithm with the introduction of a free choice of the variable to which to backtrack in case of inconsistency, or (ii) as a local search algorithm in the space of the partial consistent variable assignments. or (iii) as a hybridisation between local...
About the maximum information and maximum likelihood principles
Neural networks with radial basis functions are considered, and the Shannon information in their output concerning input. The role of information- preserving input transformations is discussed when the network is specified by the maximum information principle and by the maximum likelihood principle. A transformation is found which simplifies the input structure in the sense that it minimizes the entropy in the class of all information-preserving transformations. Such transformation need not be unique...
About the use of neural networks in integrated numerical circuits and systems.
Abstract action potential models for toxin recognition.
Accelerating backtrack search with a best-first-search strategy
Adaptive control of system entropy
Advanced inference in fuzzy systems by rule base compression.
Agent-oriented abstraction.
We define an agent-oriented abstraction formalism devoted to generalized theories of abstraction that have been proposed in Artificial Intelligence. The model we propose extends the abstraction capabilities of the existing Agent-Oriented Programming paradigm. This short note reviews first the existing attempts to define abstraction in AI and in agent systems. Then, our model is introduced in terms of six definitions covering the concepts of agents, annotated knowledge, utility and society of agents....
Aggregation, Non-Contradiction and Excluded-Middle.
This paper investigates the satisfaction of the Non-Contradiction (NC) and Excluded-Middle (EM) laws within the domain of aggregation operators. It provides characterizations both for those aggregation operators that satisfy NC/EM with respect to (w.r.t.) some given strong negation, as well as for those satisfying them w.r.t. any strong negation. The results obtained are applied to some of the most important known classes of aggregation operators.
Aggregation Operators and Lipschitzian Conditions.
Aggregations preserving classes of fuzzy relations
We consider aggregations of fuzzy relations using means in [0,1] (especially: minimum, maximum and quasilinear mean). After recalling fundamental properties of fuzzy relations we examine means, which preserve reflexivity, symmetry, connectedness and transitivity of fuzzy relations. Conversely, some properties of aggregated relations can be inferred from properties of aggregation results. Results of the paper are completed by suitable examples and counter- examples, which is summarized in a special...
AI clustering techniques: a new approach in horizontal fragmentation of classes with complex attributes and methods in object oriented databases.
Algebraic analysis of LPC+Ch calculus
Algorithmes génétiques hybrides pour l'optimisation combinatoire
Algorithms for Classification based on k-NN.
Alternative definitions of conditional possibilistic measures
The aim of this paper is to survey and discuss, very briefly, some ways how to introduce, within the framework of possibilistic measures, a notion analogous to that of conditional probability measure in probability theory. The adjective “analogous” in the last sentence is to mean that the conditional possibilistic measures should play the role of a mathematical tool to actualize one’s degrees of beliefs expressed by an a priori possibilistic measure, having obtained some further information concerning...