This paper presents a method for pattern discovery based on viewpoints and feature set patterns. The representation for pattern components accommodates in a fully general way the taxonomic relationships that may exist between interval classes. A heuristic probabilistic hill climbing algorithm is developed to rapidly direct the search towards interesting patterns. The method can be used for sing...

Cohesive subgroups have always represented an important construct for sociologists who study individuals and organizations. In this article, I apply recent advances in the statistical modell ing of social network data to the task of identifying cohesive subgroups from social network data. Further, through simulated data, I describe a process for obtaining the probability that a given sample of ...

The induction of classification rules has been dominated by a single generic technique—the covering algorithm. This approach employs a simple hill-climbing search to learn sets of rules. Such search is subject to numerous widely known deficiencies. Further, there is a growing body of evidence that learning redundant sets of rules can improve predictive accuracy. The ultimate end-point of a move...

We evaluate different call admission control policies in various multiservice cellular scenarios. For each of the studied policies we obtain the maximum calling rate that can be offered to the system to achieve a given QoS objective defined in terms of blocking probabilities. We propose an optimization methodology based on a hill climbing algorithm to find the optimum configuration for most pol...

This paper investigates the problem of policy learning in multi-agent environments using the stochastic game framework, which we brieey overview. We introduce two properties as desirable for a learning agent when in the presence of other learning agents, namely rationality and convergence. We examine existing reinforcement learning algorithms according to these two properties and notice that th...

Adaptive search heuristics are known to be valuable in approximating solutions to hard search problems. However, these techniques are problem dependent. Inspired by the idea of life cycle stages found in nature, we introduce a hybrid approach called the LifeCycle model that simultaneously applies genetic algorithms (GAs), particle swarm optimisation (PSOs), and stochastic hill climbing to creat...

An experimental study of a sand bed submitted to a transient water shear flow in a vertical axis cylindrical container is reported. The appearance of spontaneous phase segregation in the spiral ripple patterns is shown. Larger grains are observed to segregate on the downstream part of the ripples, while the smaller ones segregate on the upstream part. The relative repose angles between sand spe...

An experimental study of a binary granular mixture submitted to a transient shear flow in a cylindrical container is reported. The formation of ripples with a spiral shape is observed. The appearance of phase segregation in those spiral patterns is shown. The relative grain size bewteen sand species is found to be a relevant parameter leading to phase segregation. However, the relative repose a...

A number of non-exhaustive search algorithms are presented. The methods are a c̀lassical’ genetic algorithm, a tabu search, an evolutionary strategy and stochastically repeated nearest and steepest-ascent hill-climbing algorithms. They are then used to determine optimum and good polarities for Reed± Muller canonical expansions of Boolean functions, and comparisons are drawn between the relative ...

Genetic algorithms have particular potential as a tool for optimization when the evaluation function is noisy. Several types of genetic algorithm are compared against a mutation driven stochastic hill-climbing algorithm on a standard set of benchmark functions which have had Gaussian noise added to them. Diierent criteria for judging the eeectiveness of the search are also considered. The genet...