Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Neural networks (2)
- AI technology (1)
- Applications (1)
- Bus structures (1)
- Comparability graphs (1)
-
- Design mechanisms (1)
- Design processes (1)
- Distributed operating systems (1)
- Dynamics (1)
- Execution time (1)
- Graphic workstations (1)
- Graphs (1)
- High performance issues (1)
- Hopefield networks (1)
- Image processing (1)
- Intelligent monitoring (1)
- Learning (1)
- Machine learning (1)
- Mathematical models (1)
- Mesh architectures (1)
- Monitoring computer systems (1)
- Multigrid algorithms (1)
- Parallel algorithms (1)
- Parallel machines (1)
- Pattern recognition (1)
- Polygon (1)
- Recognition algorithm (1)
- Reconfigurable meshes (1)
- Sources (1)
- Statistical pattern classification (1)
- Publication
- Publication Type
Articles 1 - 13 of 13
Full-Text Articles in Physical Sciences and Mathematics
Multiple Learner Systems Using Resampling Methods, Binyun Xie
Multiple Learner Systems Using Resampling Methods, Binyun Xie
Computer Science Theses & Dissertations
The N-Learners Problem deals with combining a number of learners such that the resultant system is "better", under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, …
Multigrid Algorithms For Massively Parallel Machines, Satyanarayan Gupta
Multigrid Algorithms For Massively Parallel Machines, Satyanarayan Gupta
Computer Science Theses & Dissertations
Numerical solutions of partial differential equations (pde's) are required in many physical problems arising in areas such as computational fluid dynamics, atmospheric sciences, electromagnetics etc. One of the most popular methods of solving pde's is the use of the multigrid algorithm. However, the implementation of the multigrid algorithm on massively parallel machines is not very efficient because of (i) low processor utilization and (ii) high communication overheads. These problems need to be addressed to make better use of massively parallel machines for solving pde's using the multigrid algorithm.
In this dissertation, we present three parallel multigrid algorithms which …
High Performance Issues On Parallel Architectures, Peter J. Looges
High Performance Issues On Parallel Architectures, Peter J. Looges
Computer Science Theses & Dissertations
In an effort to reduce communication latency in mesh-type architectures, these architectures have been augmented by various types of global and reconfigurable bus structures. The static bus structures provide excellent performance in many areas of computation especially structured numerical computations, but they lack the flexibility required of many large numerical and non-numerical applications. Reconfigurable bus systems have the dynamic adaptability to handle a much wider range of applications. While reconfigurable meshes can often yield constant time results for many problems, the cost of this performance is paid in the number of processors required. While in actuality the majority of these …
Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi
Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi
Electrical & Computer Engineering Theses & Dissertations
This dissertation introduces a binary partitioned approach to statistical pattern classification which is applied to talker identification using neural networks. In recent years artificial neural networks have been shown to work exceptionally well for small but difficult pattern classification tasks. However, their application to large tasks (i.e., having more than ten to 20 categories) is limited by a dramatic increase in required training time. The time required to train a single network to perform N-way classification is nearly proportional to the exponential of N. In contrast, the binary partitioned approach requires training times on the order of N2. …
Visual Graphic Knowledge Management Methodology, Jih-Shih Hsu
Visual Graphic Knowledge Management Methodology, Jih-Shih Hsu
Computer Science Theses & Dissertations
As computer technology evolves, graphic workstations are becoming more popular. They support more friendly user interfaces than do conventional terminals. The better user interfaces require more effort to develop. Therefore, many user interface (UI) design systems have been developed to facilitate the creation of modern user interfaces, but not very successfully. Many of them either provide limited features or are difficult to use. Besides, these UI design systems are actually like black boxes to their users because the underlying technology is opaque; their users cannot learn how to utilize the underlying window systems through user interface design sessions. In a …
Single Object Detection Using Multiple Sensors With Unknown Noise Distributions, Shaofen Chen
Single Object Detection Using Multiple Sensors With Unknown Noise Distributions, Shaofen Chen
Computer Science Theses & Dissertations
We consider the design of an object classification system that identifies single objects using a system of sensors; each sensor outputs a random vector, according to an unknown (noise) probability distribution, in response to a sensed object. We consider a special class of systems, called the linearly separable systems, where the error-free sensor outputs corresponding to distinct objects can be mapped into disjoint intervals on real line. Given a set of sensor outputs corresponding to known objects, we show that a detection rule αemp that approaches the correct rule with a high probability can be computed. We show …
Reasoning By Analogy In A Multi-Level System Architecture For The Design Of Mechanisms, Ghassan F. Issa
Reasoning By Analogy In A Multi-Level System Architecture For The Design Of Mechanisms, Ghassan F. Issa
Computer Science Theses & Dissertations
Since the first attempts to integrate AI technology and engineering design nearly two decades ago, few expert systems have been shown to demonstrate sufficient reasoning capabilities to solve real-world design problems. The complex nature of design, the lack of understanding of the design process, and the limitations of current expert system technology have all been shown to have adverse effects on the maturity of this research area. Therefore, our direction in this research concentrates on understanding the design process, investigating a novel area of research focusing on creative design, and incorporating the results into a system model feasible for production …
Monitoring Computer Systems: An Intelligent Approach, Myron Zhihong Xu
Monitoring Computer Systems: An Intelligent Approach, Myron Zhihong Xu
Computer Science Theses & Dissertations
Monitoring modern computer systems is increasingly difficult due to their peculiar characteristics. To cope with this situation, the dissertation develops an approach to intelligent monitoring. The resulting model consists of three major designs: representing targets, controlling data collection, and autonomously refining monitoring performance. The model explores a more declarative object-oriented model by introducing virtual objects to dynamically compose abstract representations, while it treats conventional hard-wired hierarchies and predefined object classes as primitive structures. Taking the representational framework as a reasoning bed, the design for controlling mechanisms adopts default reasoning backed up with ordered constraints, so that the amount of data …
The Morphology Of Convex Polygons, Stephan Olariu
The Morphology Of Convex Polygons, Stephan Olariu
Computer Science Faculty Publications
A simple polygon P is said to be unimodal if for every vertex of P, the Euclidian distance function to the other vertices of P is unimodal. The study of unimodal polygons has emerged as a fruitful area of computational and discrete geometry. We study unimodality properties of a number of special convex polygons from the morphological point of view. In particular, we establish a hierarchy among three classes of convex polygons in terms of their unimodality properties.
A Tree Representation For P4-Sparse Graphs, B. Jamison, Stephan Olariu
A Tree Representation For P4-Sparse Graphs, B. Jamison, Stephan Olariu
Computer Science Faculty Publications
A graph G is P4-sparse if no set of five vertices in G induces more than one chordless path of length three. P4-sparse graphs generalize both the class of cographs and the class of P4-reducible graphs. We give several characterizations for P4-sparse graphs and show that they can be constructed from single-vertex graphs by a finite sequence of operations. Our characterization implies that the P4-sparse graphs admit a tree representation unique up to isomorphism. Furthermore, this tree representation can be obtained in polynomial time.
Bounds On Constraint Weight Parameters Of Hopfield Networks For Stability Of Optimization Problem Solutions, Gursel Serpen
Bounds On Constraint Weight Parameters Of Hopfield Networks For Stability Of Optimization Problem Solutions, Gursel Serpen
Electrical & Computer Engineering Theses & Dissertations
The purpose of the presented research is to study the convergence characteristics of Hopfield network dynamics. The relation between constraint weight parameter values and the stability of solutions of constraint satisfaction and optimization problems mapped to Hopfield networks is investigated. A theoretical development relating constraint weight parameter values to solution stability is presented. The dependency of solution stability on constraint weight parameter values is shown employing an abstract optimization problem. A theorem defining bounds on the constraint weight parameter magnitudes for solution stability of constraint satisfaction and optimization problems is proved. Simulation analysis on a set of optimization and constraint …
On Sources In Comparability Graphs, With Applications, Stephan Olariu
On Sources In Comparability Graphs, With Applications, Stephan Olariu
Computer Science Faculty Publications
We characterize sources in comparability graphs and show that our result provides a unifying look at two recent results about interval graphs.
High Performance Issues In Image Processing And Computer Vision, Jingyuan Zhang
High Performance Issues In Image Processing And Computer Vision, Jingyuan Zhang
Computer Science Theses & Dissertations
Typical image processing and computer vision tasks found in industrial, medical, and military applications require real-time solutions. These requirements have motivated the design of many parallel architectures and algorithms. Recently, a new architecture called the reconfigurable mesh has been proposed. This thesis addresses a number of problems in image processing and computer vision on reconfigurable meshes.
We first show that a number of low-level descriptors of a digitized image such as the perimeter, area, histogram and median row can be reduced to computing the sum of all the integers in a matrix, which in turn can be reduced to computing …