This thesis proposes the evaluation and comparison of software process engineering support tools and environments. The two dimensions our work focuses on are the goals pursued when processes are engineered, and the roles, related to software processes, played in a…

This thesis studies the introduction of a priori structure into the design of learning systems based on artificial neural networks applied to sequence recognition, in particular to phoneme recognition in continuous speech. Because we are interested in sequence analysis, algorithms…

Speaker-independence and large lexicon access are still two of the greatest problems in automatic speech recognition. Cognitive and information-theory approaches try to solve the recognition problem by proceeding in almost opposite directions. The former rely on knowledge representation, reasoning and…

AI planning benefits greatly from the use of temporally-extended or macro-actions. Macro-actions allow for faster and more efficient planning as well as the reuse of knowledge from previous solutions. In recent years, a significant amount of research has been devoted…

Most routers, to our knowledge, are difficult for researchers and students without root privileges to implement or modify, because their implementation is in kernel space. GINI is an innovative platform on conventional PCs, which brings the whole functionality of a…

In this thesis, we introduce SableJIT, a retargetable just-in-time compiler for the SableVM Java virtual machine. Our design attempts to minimize the amount of work required to port (or to retarget) our compiler to a new platform. We accomplish this…

Reinforcement Learning is a class of methods for solving sequential decision problems when the model of the environment is not known. In this framework, the agent must explore the environment to gather more information about the model and the utility…

The incorporation of temporally extended actions, or options , into the reinforcement learning framework has proven to be useful in planning and knowledge representation. Options provide a form of temporal abstraction, as they represent courses of action of variable duration.…

"Model Driven Software Development" is a recent trend in development of software-intensive systems. In the Model Driven Software Development process, all knowledge pertaining to the software system to be built is represented in the form of models, in the right…

People are efficient when they make decisions under uncertainty, even when their decisions have long-term ramifications, or when their knowledge and their perception of the environment are uncertain. We are able to experiment with the environment and learn, improving our…