# Browse Dept. of Computer Science by Title

• (1992)
This thesis describes CAM (Categories, Agreement, and Morphology), a computer model of several aspects of language acquisition. CAM is based on the Semantic Bootstrapping Hypothesis (Pinker, 1984), and CAM also respects ...

application/pdf

PDF (9Mb)
• (1993)
One of the obstacles to be overcome in Natural Language Understanding is the existence of lexical gaps; that is, words or word senses which are not in the lexicon of the system. No lexicon, whether hand-coded or derived ...

application/pdf

PDF (14Mb)
• (1982)
One of the problems in building a general purpose operating system is the construction of interfaces between programs that are interdependent but are loaded at different times. This thesis presents a model that generalizes ...

application/pdf

PDF (4Mb)
• (2005-05)
In neighborhood-based texture synthesis, adjacent local regions need to satisfy color continuity constraints in order to avoid visible seams. Such continuity constraints seriously restrict the variability of synthesized ...

application/pdf

PDF (434Kb)
• (2010-05)
This dissertation investigates novel approaches for analysis and visualization of two kinds of graph, scale-free network and rooted hierarchy, at large scales with thousands to millions of nodes. Scale-free network, ...

application/pdf

PDF (13Mb)
• (2010-05-19)
This dissertation investigates novel approaches for analysis and visualization of two kinds of graph, scale-free network and rooted hierarchy, at large scales with thousands to millions of nodes. Scale-free network, ...

application/pdf

PDF (13Mb)
• (2012-05-22)
Large lectures are a difficult and complicated area of exploration, both technologically and socially. Here is presented a discussion of existing areas of investigation related to large lectures, including fostering crowd ...

application/pdf

PDF (1Mb)
• (2006-12)
The Web has been rapidly deepened'' by myriad searchable databases online, where data are hidden behind query interfaces. Guarding data behind them, such query interfaces are the entrances'' or doors'' to the deep ...

application/pdf

PDF (2Mb)
• (2013-08-22)
Large-scale networks, such as the Internet, cellular networks, play critical roles in today's life. The advancement of large-scale computer and communication networks heavily depends on the successful transformation from ...

application/pdf

PDF (9Mb)
• (2012-05-07)
Network algorithms are deployed on large networks, and proper algorithm evaluation is necessary to avoid large-scale outages or performance bottlenecks. However, evaluating a network algorithm in a simulator results ...

application/pdf

PDF (261Kb)
• (2006-01)
The computational bottleneck of topology optimization is the solution of a large number of linear systems arising in the finite element analysis. We propose fast iterative solvers for large three-dimensional topology ...

application/pdf

PDF (4Mb)
• (2013-01-24)
With the fast growth of (online) content and the need for high quality content services, cloud data centers are increas- ingly becoming the preferred places to store data and re- trieve it from. With a highly variable ...

application/pdf

PDF (576Kb)
• (1983)
The NMOS Gate-Cell, a regular structure that supports gate level implementations of random logic is introduced. It is an extension of the Weinberger array, where allowing input/output terminals on all four edges resulted ...

application/pdf

PDF (4Mb)
• (2006-05)
Transactional memory (TM) is a compelling alternative to traditional synchronization, and implementing TM primitives directly in hardware offers a potential performance advantage over software-based methods. In this paper, ...

application/pdf

PDF (200Kb)
• (2005-05)
Information extraction is a process that extracts limited semantic concepts from text documents and presents them in an organized way. Unlike several other natural language tasks, information extraction has a direct impact ...

application/pdf

PDF (495Kb)
• (2012-02-06)
Machine learning (ML) is the study of representations and algorithms used for building functions that improve their behavior with experience. Today, researchers in many domains are applying ML to solve their problems when ...

application/pdf

PDF (1Mb)
• (1989)
This thesis describes a new class of Intelligent Tutoring Systems (ITS) which I call the Learning Companion Systems (LCS). In the learning environment of such a system, there are three agents involved, namely, the human ...

application/pdf

PDF (7Mb)
• (2013-06-25)

application/pdf

PDF (631Kb)
• (1990)
This thesis describes an exploration of methods involved in learning flexible concepts that is an important and less explored area in machine learning. The two approaches described in this thesis are based on the idea of ...

application/pdf

PDF (8Mb)
• (2013-02-03)
In this work we take a first step towards Learning from Natural Instructions (LNI), a framework for communicating human knowledge to computer systems using natural language. In this framework the process of learning is ...

application/pdf

PDF (1Mb)