We present a framework that is able to discover the latent factors that parametrize a family of related tasks from data. The resulting model is able to rapidly identify the dynamics of a new task instance, allowing an agent to flexibly adapt to task variations.

This paper discusses the use of factorization techniques in distributional semantic models. We focus on a method for redistributing the weight of latent variables, which has previously been shown to improve the performance of distributional semantic models. However, this result has not been replicated and remains poorly understood. We refine the method, and provide additional theoretical justif...

The present research examined the reliability of three types of divergent thinking tasks (unusual uses, instances, consequences/implications) and two types of subjective scoring (an average across all responses vs. the responses people chose as their top-two responses) within a latent variable framework, using the maximal-reliability H statistic. Overall, the unusual uses tasks performed the be...

Résumé. Cet article propose une méthode de régression non linéaire qui s’appuie sur un modèle intégrant un processus latent qui permet d’activer préférentiellement, et de manière souple, des sous-modèles de régression polynomiaux. Les paramètres du modèle sont estimés par la méthode du maximum de vraisemblance mise en œuvre par un algorithme EM dédié. Une étude expérimentale menée sur des donné...