Most neural network learning algorithms cannot use knowledge other than what is provided in the training data. Initialized using random weights, they cannot use prior knowledge such as knowledge stored in previously trained networks. This manuscript thesis addresses this problem.…

2007

Une préoccupation essentielle traverse cette thèse: l'indifférence systémique de la Loi internationale sur la propriété intellectuelle a l'égard des savoirs traditionnels autochtones. De manière générale, un écart semble d'ailleurs croissant entre l'importance des accords internationaux sur les questions d'intérêt commercial…

Le contexte culturel particulier à la Chine influe sur le choix du mode de résolution des différends commerciaux comportant un lien d'extranéité. Plusieurs mécanismes de préventions des litiges sont utilisés en Chine. La conciliation et médiation sont issues d'une tradition…

El presente trabajo aborda el conocimiento; relaciones, representaciones y valoraciones que alumnos y docentes realizan en el contexto de la cotidianeidad escolar, integrando el proyecto de investigación "Adolescencia y Escuela" que se viene implementando desde 1995, en la cátedra Fundamentos…

Cultural resources like traditional medicinal knowledge need to be recognized in their role tied to important regional practices in Zimbabwe. This is especially as a nexus of legal definitions for biological, intellectual and cultural resources will inform a National Sui…

This dissertation addresses the issues pertaining to composite products (CPs). CPs are defined as products formed by combining knowledge from two distinct domains, for example, digital cameras, which combine knowledge from digital products and cameras. The three research questions addressed…

This paper presents a proposal for an architecture that integrates knowledge discovery systems (automatic acquisition) and knowledge based systems (experts systems). This work formulates considerations over the viability of the implementation of this architecture according to the advance of the…

In this paper, a supervised learning system of word sense disambiguation is presented. It is based on conditional maximum entropy models. This system acquires the linguistic knowledge from an annotated corpus and this knowledge is represented in the form of…

This thesis is a theoretical and practical investigation of the role played by informal learning and teaching in the development of identity and applied knowledge. With the advent of mass schooling, there came to be a distinction between formal and…