If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have…

In this research line we are exploring the possibility of having multiple preference criteria to compare arguments in in Defeasible Argumentation. In this work we are assuming a goaloriented Argumentative System, to which an application or an agent may seek…

by Tung Chan., Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1995., Includes bibliographical references (leaves 99-102).

his dissertation analyzes how local knowledge improves environmental decisions. The premise is that controlling pollution and addressing public health disparities are not problems that professionals alone can solve. Concerned lay publics, especially low-income populations and people of color that experience…

Heterogeneous azeotropic distillation is a widely used technique to separate binary azeotropic mixtures into their components. One of its most important applications is the dehydration of ethanol, which is blended with gasoline to obtain automobile fuel. Among all the compounds…

Banking channel management has become a crucial component in the drive for improved efficiency. Since the channel is the interlocutor between customers and products, banks are leveraging their knowledge of channels to efficiently address perfect product portfolio through the most…

This dissertation considers three implications of collective self-government for just foreign policies in an imperfect world. Individuals are the appropriate moral unit of analysis, constrained to govern themselves justly, together with compatriots. First I derive limits to state autonomy that…

by Kimberly G. Waters., Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002., Includes bibliographical references (p. 45-46).

Conversational interfaces have received much attention as a promising natural communication channel between humans and computers. A typical conversational interface consists of three major systems: speech understanding, dialog management and spoken language generation. In such a conversational interface, speech recognition…

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.…