In order to understand and create human-level intelligence I have developed the Polyscheme cognitive architecture to build systems that combine several representation and inference schemes when they think. Polyscheme is based on three principles. First, different (aspects of) situations that…

by Brian Cantwell Smith., Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1982., MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING., Bibliography: leaves 756-761.

This thesis focuses on the search for a more equitable urban environment. In Western Europe, the hope that cities are relevant forms of living and interacting, still exists. In Brussels, in the last fifteen years, the inhabitants formed a unique…

Evaluating of Recurrent Selection (RS) programs can lead to increase knowledge of methods, populations, and traits and give support for better management of breeding programs. The objective herein was to evaluate the effects of seven cycles of half-sib selection followed…

This study was designed to examine the ability to use prior knowledge in text comprehension and knowledge integration. The focus of the research was on effects of different degrees of subjects' theoretical knowledge in the domain of biochemistry on their…

Drawing on an empirical study on automakers? management of supplier
involvement in product development in Japan, this paper shows that when the design of
a component is outsourced to a supplier, how much and what automakers know about
the component…

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…

by Jeffrey C. Chi., Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Civil and Environmental Engineering, 2001., Includes bibliographical references (p. 199-216).

This study investigated the underlying factor structure of second language (L2) cloze test performance as explained by a theoretical model including the following hypothetical constructs: cloze-taking ability, knowledge of language, knowledge of text content, and knowledge of contextual constraints. Eight…

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.…