This thesis presents a development environment for Design Expert Systems that features a new language where the roles of knowledge and the way it is brought to bear are predefined by the solution method., The language also allows knowledge to…

Over the past few years, the amount of electronic information available from the Internet has increased dramatically. Unfortunately, the search tools currently available for retrieving and filtering such information remain inadequate in balancing relevance and comprehensiveness. This work proposes a…

This thesis explores the use of randomized, performance-based search strategies to improve the generalization of an automatic speech recognition system based on hidden Markov models. We apply simulated annealing and random search to several components of the system, including phoneme…

Passively accepting measurements of the world is not enough, as the data obtained is always incomplete, and the inferences made from it uncertain to a degree which is often unacceptable. Machines that operate autonomously will always be faced with this…

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…

Since there exist drawbacks for linear models such as those based on regression techniques, which have been the basis of traditional statistical forecasting models, neural networks are used in this thesis to train and test the input data. This thesis…

There are basically three areas which can be explored to improve an HMM based recognizer, namely, parameter extraction, training methods and vocabulary representation., The goal of parameter extraction is not only to find a compact and robust parametric representation of…