Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

Faculty Publications

Discipline
Institution
Keyword
Publication Year
File Type

Articles 571 - 600 of 663

Full-Text Articles in Computer Sciences

Improving The Hopfield Network Through Beam Search, Tony R. Martinez, Xinchuan Zeng Jul 2001

Improving The Hopfield Network Through Beam Search, Tony R. Martinez, Xinchuan Zeng

Faculty Publications

In this paper we propose a beam search mechanism to improve the performance of the Hopfield network for solving optimization problems. The beam search readjusts the top M (M > 1) activated neurons to more similar activation levels in the early phase of relaxation, so that the network has the opportunity to explore more alternative, potentially better solutions. We evaluated this approach using a large number of simulations (20,000 for each parameter setting), based on 200 randomly generated city distributions of the 10-city traveling salesman problem. The results show that the beam search has the capability of significantly improving the network …

Go to article

Improved Hopfield Networks By Training With Noisy Data, Fred Clift, Tony R. Martinez Jul 2001

Improved Hopfield Networks By Training With Noisy Data, Fred Clift, Tony R. Martinez

Faculty Publications

A new approach to training a generalized Hopfield network is developed and evaluated in this work. Both the weight symmetricity constraint and the zero self-connection constraint are removed from standard Hopfield networks. Training is accomplished with Back-Propagation Through Time, using noisy versions of the memorized patterns. Training in this way is referred to as Noisy Associative Training (NAT). Performance of NAT is evaluated on both random and correlated data. NAT has been tested on several data sets, with a large number of training runs for each experiment. The data sets used include uniformly distributed random data and several data sets …

Go to article

Lazy Training: Improving Backpropagation Learning Through Network Interaction, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer Jul 2001

Lazy Training: Improving Backpropagation Learning Through Network Interaction, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer

Faculty Publications

Backpropagation, similar to most high-order learning algorithms, is prone to overfitting. We address this issue by introducing interactive training (IT), a logical extension to backpropagation training that employs interaction among multiple networks. This method is based on the theory that centralized control is more effective for learning in deep problem spaces in a multi-agent paradigm. IT methods allow networks to work together to form more complex systems while not restraining their individual ability to specialize. Lazy training, an implementation of IT that minimizes misclassification error, is presented. Lazy training discourages overfitting and is conducive to higher accuracy in multiclass problems …

Go to article

Speed Training: Improving The Rate Of Backpropagation Learning Through Stochastic Sample Presentation, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer Jul 2001

Speed Training: Improving The Rate Of Backpropagation Learning Through Stochastic Sample Presentation, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer

Faculty Publications

Artificial neural networks provide an effective empirical predictive model for pattern classification. However, using complex neural networks to learn very large training sets is often problematic, imposing prohibitive time constraints on the training process. We present four practical methods for dramatically decreasing training time through dynamic stochastic sample presentation, a technique we call speed training. These methods are shown to be robust to retaining generalization accuracy over a diverse collection of real world data sets. In particular, the SET technique achieves a training speedup of 4278% on a large OCR database with no detectable loss in generalization.

Go to article

On The Utility Of Entanglement In Quantum Neural Computing, Dan A. Ventura Jul 2001

On The Utility Of Entanglement In Quantum Neural Computing, Dan A. Ventura

Faculty Publications

Efforts in combining quantum and neural computation are briefly discussed and the concept of entanglement as it applies to this subject is addressed. Entanglement is perhaps the least understood aspect of quantum systems used for computation, yet it is apparently most responsible for their computational power. This paper argues for the importance of understanding and utilizing entanglement in quantum neural computation.

Go to article

An Evaluation Of Shared Multicast Trees With Multiple Active Cores, Daniel Zappala, Aaron Fabbri Jul 2001

An Evaluation Of Shared Multicast Trees With Multiple Active Cores, Daniel Zappala, Aaron Fabbri

Faculty Publications

Core-based multicast trees use less router state, but have significant drawbacks when compared to shortest-path trees, namely higher delay and poor fault tolerance. We evaluate the feasibility of using multiple independent cores within a shared multicast tree. We consider several basic designs and discuss how using multiple cores improves fault tolerance without sacrificing router state. We examine the performance of multiple-core trees with respect to single-core trees and find that adding cores significantly lowers delay without increasing cost. Moreover, it takes only a small number of cores, placed with a k-center approximation, for a multiple-core tree to have lower delay …

Go to article

Effective Bandwidth For Traffic Engineering, Mark J. Clement, Rob Kunz, Seth Nielson, Quinn O. Snell May 2001

Effective Bandwidth For Traffic Engineering, Mark J. Clement, Rob Kunz, Seth Nielson, Quinn O. Snell

Faculty Publications

In today’s Internet, demand is increasing for guarantees of speed and efficiency. Current routers are very limited in the type and quantity of observed data they can provide, making it difficult for providers to maximize utilization without the risk of degraded throughput. This research uses statistical data currents provided by router vendors to estimate the impact of changes in network configuration on the probability of link overflow. This allows service providers to calculate in advance, the effect of grooming on a network, eliminating the conservative trial-and-error approach normally used. These predictions are made using Large Deviation Theory, which focuses on …

Go to article

Image Reconstruction Using Data-Dependent Triangulation, Thomas W. Sederberg, Xiaohua Yu, Bryan S. Morse May 2001

Image Reconstruction Using Data-Dependent Triangulation, Thomas W. Sederberg, Xiaohua Yu, Bryan S. Morse

Faculty Publications

Image reconstruction based on data-dependent triangulation with new cost functions and optimization can create higher quality images than traditional bilinear or bicubic spline reconstruction. The article presents a novel method for image reconstruction using a piecewise linear intensity surface whose elements don't generally align with the coordinate axes. This method is based on the technique of data-dependent triangulation (DDT) that N. Dyn et al. (1990) introduced and has proven capable of producing more pleasing reconstructions than axis-aligned methods.

Go to article

Interpolating Implicit Surfaces From Scattered Surface Data Using Compactly Supported Radial Basis Functions, Bryan S. Morse, David T. Chen, Penny Rheingans, Kalpathi Subramanian, Terry S. Yoo May 2001

Interpolating Implicit Surfaces From Scattered Surface Data Using Compactly Supported Radial Basis Functions, Bryan S. Morse, David T. Chen, Penny Rheingans, Kalpathi Subramanian, Terry S. Yoo

Faculty Publications

We describe algebraic methods for creating implicit surfaces using linear combinations of radial basis interpolants to form complex models from scattered surface points. Shapes with arbitrary topology are easily represented without the usual interpolation or aliasing errors arising from discrete sampling. These methods were first applied to implicit surfaces by Savchenko, et al. and later developed independently by Turk and O'Brien as a means of performing shape interpolation. Earlier approaches were limited as a modeling mechanism because of the order of the computational complexity involved. We explore and extend these implicit interpolating methods to make them suitable for systems of …

Go to article

Parallel Phylogenetic Inference, Mark J. Clement, David Mclaughlin, Quinn O. Snell, Michael Whiting Nov 2000

Parallel Phylogenetic Inference, Mark J. Clement, David Mclaughlin, Quinn O. Snell, Michael Whiting

Faculty Publications

Recent advances in DNA sequencing technology have created large data sets upon which phylogenetic inference can be performed. However, current research is limited by the prohibitive time necessary to perform tree search on even a reasonably sized data set. Some parallel algorithms have been developed but the biological research community does not use them because they don’t trust the results from newly developed parallel software. This paper presents a new phylogenetic algorithm that allows existing, trusted phylogenetic software packages to be executed in parallel using the DOGMA parallel processing system. The results presented here indicate that data sets that currently …

Go to article

Toward Automated Abstraction For Protocols On Branching Networks, Michael D. Jones, Ganesh Gopalakrishnan Nov 2000

Toward Automated Abstraction For Protocols On Branching Networks, Michael D. Jones, Ganesh Gopalakrishnan

Faculty Publications

We have used various manual abstraction techniques to formally verify a transaction ordering property for an IO protocol over bus/bridge networks. In the context of network protocol verification, an abstraction is needed to reduce the unbounded number of network configurations to a small number of representative networks that can be checked using algorithmic methods. The manually derived abstraction was both brittle and difficult to validate. In this report, we discuss the need for abstraction techniques in the formal verification of protocols over networks and present our recent efforts to create an automatic abstraction technique for network protocols using predicate abstraction …

Go to article

Optically Simulating A Quantum Associative Memory, Dan A. Ventura, John C. Howell, John A. Yeazell Sep 2000

Optically Simulating A Quantum Associative Memory, Dan A. Ventura, John C. Howell, John A. Yeazell

Faculty Publications

This paper discusses the realization of a quantum associative memory using linear integrated optics. An associative memory produces a full pattern of bits when presented with only a partial pattern. Quantum computers have the potential to store large numbers of patterns and hence have the ability to far surpass any classical neural network realization of an associative memory. In this work two 3-qubit associative memories will be discussed using linear integrated optics. In addition, corrupted, invented and degenerate memories are discussed.

Go to article

Rescaling The Energy Function In Hopfield Networks, Tony R. Martinez, Xinchuan Zeng Jul 2000

Rescaling The Energy Function In Hopfield Networks, Tony R. Martinez, Xinchuan Zeng

Faculty Publications

In this paper we propose an approach that rescales the distance matrix of the energy function in the Hopfield network for solving optimization problems. We rescale the distance matrix by normalizing each row in the matrix and then adjusting the parameter for the distance term. This scheme has the capability of reducing the effects of clustering in data distributions, which is one of main reasons for the formation of invalid solutions. We evaluate this approach through a large number (20,000) simulations based on 200 randomly generated city distributions of the 10-city traveling salesman problem. The result shows that, compared to …

Go to article

The Inefficiency Of Batch Training For Large Training Sets, Tony R. Martinez, D. Randall Wilson Jul 2000

The Inefficiency Of Batch Training For Large Training Sets, Tony R. Martinez, D. Randall Wilson

Faculty Publications

Multilayer perceptrons are often trained using error backpropagation (BP). BP training can be done in either a batch or continuous manner. Claims have frequently been made that batch training is faster and/or more "correct" than continuous training because it uses a better approximation of the true gradient for its weight updates. These claims are often supported by empirical evidence on very small data sets. These claims are untrue, however, for large training sets. This paper explains why batch training is much slower than continuous training for large training sets. Various levels of semi-batch training used on a 20,000-instance speech recognition …

Go to article

Almost Block Diagonal Linear Systems: Sequential And Parallel Solution Techniques, And Applications, P. Amodio, J.R. Cash, G. Roussos, R.W. Wright, G. Fairweather, I. Gladwell, G.L. Kraut, M. Paprzycki Jul 2000

Almost Block Diagonal Linear Systems: Sequential And Parallel Solution Techniques, And Applications, P. Amodio, J.R. Cash, G. Roussos, R.W. Wright, G. Fairweather, I. Gladwell, G.L. Kraut, M. Paprzycki

Faculty Publications

Almost block diagonal (ABD) linear systems arise in a variety of contexts, specifically in numerical methods for two-point boundary value problems for ordinary differential equations and in related partial differential equation problems. The stable, efficient sequential solution of ABDs has received much attention over the last fifteen years and the parallel solution more recently. We survey the fields of application with emphasis on how ABDs and bordered ABDs (BABDs) arise. We outline most known direct solution techniques, both sequential and parallel, and discuss the comparative efficiency of the parallel methods. Finally, we examine parallel iterative methods for solving BABD systems. …

Go to article

Roughening, Deroughening, And Nonuniversal Scaling Of The Interface Width In Electrophoretic Deposition Of Polymer Chains, Frank W. Bentrem, Ras B. Pandey, Fereydoon Family Jul 2000

Roughening, Deroughening, And Nonuniversal Scaling Of The Interface Width In Electrophoretic Deposition Of Polymer Chains, Frank W. Bentrem, Ras B. Pandey, Fereydoon Family

Faculty Publications

Growth and roughness of the interface of deposited polymer chains driven by a field onto an impenetrable adsorbing surface are studied by computer simulations in (2 + 1) dimensions. The evolution of the interface width W shows a crossover from short-time growth described by the exponent beta(1) to a long-time growth with exponent beta(2) (>beta(1)) Tne saturated width increases, i.e., the interface roughens, with the molecular weight L-c, but the roughness exponent alpha (from W-s similar to L-alpha) becomes negative in contrast to models for particle deposition; cr depends on the chain length-a nonuniversal scaling with the substrate length …

Go to article

Intelligent Selection Tools, William A. Barrett, Eric N. Mortensen, L. Jack Reese Jun 2000

Intelligent Selection Tools, William A. Barrett, Eric N. Mortensen, L. Jack Reese

Faculty Publications

Intelligent Scissors and Intelligent Paint are complementary interactive image segmentation tools that allow a user to quickly and accurately select objects of interest. This demonstration provides a means for participants to experience the dynamic nature of these tools.

Go to article

3d Outside Cell Interference Factor For An Air-Ground Cdma ‘Cellular’ System, David W. Matolak May 2000

3d Outside Cell Interference Factor For An Air-Ground Cdma ‘Cellular’ System, David W. Matolak

Faculty Publications

We compute the outside-cell interference factor of a code-division multiple-access (CDMA) system for a three-dimensional (3-D) air-to-ground (AG) "cellular-like" network consisting of a set of uniformly distributed ground base stations and airborne mobile users. The CDMA capacity is roughly inversely proportional to the outside-cell interference factor. It is shown that for the nearly free-space propagation environment of these systems, the outside-cell interference factor can be larger than that for terrestrial propagation models (as expected) and depends approximately logarithmically upon both the cell height and cell radius.

Go to article

Bounding Interval Rational Bézier Curves With Interval Polynomial Bézier Curves, Thomas W. Sederberg, Falai Chen, Wenping Lou Apr 2000

Bounding Interval Rational Bézier Curves With Interval Polynomial Bézier Curves, Thomas W. Sederberg, Falai Chen, Wenping Lou

Faculty Publications

In this paper, we put forward and study the problem of bounding an interval rational Bézier curve with an interval polynomial Bézier curve. We propose three different methods—Hybrid Method, Perturbation Method and Linear Programming Method to solve this problem. Examples are illustrated to compare the three different methods. The empirical results show that the Perturbation Method and the Linear Programming Method produce much tighter bounds than the Hybrid Method, though they are computationally several times more expensive.

Go to article

Designing Human-Centered Automation: Tradeoffs In Collision Avoidance System Design, Michael A. Goodrich, Erwin R. Boer Mar 2000

Designing Human-Centered Automation: Tradeoffs In Collision Avoidance System Design, Michael A. Goodrich, Erwin R. Boer

Faculty Publications

Technological advances have made plausible the design of automated systems that share responsibility with a human operator. The decision to use automation to assist or replace a human operator in safety-critical tasks must account for not only the technological capabilities of the sensor and control subsystems, but also the autonomy, capabilities, and preferences of the human operator. By their nature, such human-centered automation problems have multiple attributes: an attribute reflecting human goals and capabilities, and an attribute reflecting automation goals and capabilities. Although good theories exist that describe portions of human behavior generation, in the absence of a general theory …

Go to article

Alternate Path Routing For Multicast, Daniel Zappala Mar 2000

Alternate Path Routing For Multicast, Daniel Zappala

Faculty Publications

Alternate path routing has been well-explored in telecommunication networks as a means of decreasing the call blocking rate and increasing network utility. However, aside from some work applying these concepts to unicast flows, alternate path routing has received little attention in the Internet community. We describe and evaluate an architecture for alternate path routing for multicast flows. For path installation, we design a receiver-oriented alternate path protocol and prove that it reconfigures multicast trees without introducing loops. For path computation, we propose a scalable local search heuristic that allows receivers to find alternate paths using only partial network information. We …

Go to article

Learning Quantum Operators, Dan A. Ventura Mar 2000

Learning Quantum Operators, Dan A. Ventura

Faculty Publications

Consider the system Fx = w where F is unknown. We examine the possibility of learning the operator F inductively, drawing analogies with ideas from classical computational learning.

Go to article

Estimating Tessellation Parameter Intervals For Rational Curves And Surfaces, Thomas W. Sederberg, Jianmin Zheng Jan 2000

Estimating Tessellation Parameter Intervals For Rational Curves And Surfaces, Thomas W. Sederberg, Jianmin Zheng

Faculty Publications

This paper presents a method for determining a priori a constant parameter interval with which a rational curve or surface can be tessellated such that the deviation of the curve or surface from its piecewise linear approximation is within a specified tolerance. The parameter interval is estimated based on information about the second order derivatives in the homogeneous coordinates, instead of using affine coordinates directly. This new step size can be found with roughly the same amount of computation as the step size presented in [Cheng 1992], though it can be proven to always be larger than Cheng's step size. …

Go to article

Cross Validation And Mlp Architecture Selection, Timothy L. Andersen, Tony R. Martinez Jul 1999

Cross Validation And Mlp Architecture Selection, Timothy L. Andersen, Tony R. Martinez

Faculty Publications

The performance of cross validation (CV) based MLP architecture selection is examined using 14 real world problem domains. When testing many different network architectures the results show that CV is only slightly more likely than random to select the optimal network architecture, and that the strategy of using the simplest available network architecture performs better than CV in this case. Experimental evidence suggests several reasons for the poor performance of CV. In addition, three general strategies which lead to significant increase in the performance of CV are proposed. While this paper focuses on using CV to select the optimal MLP …

Go to article

Extending The Power And Capacity Of Constraint Satisfaction Networks, Tony R. Martinez, Xinchuan Zeng Jul 1999

Extending The Power And Capacity Of Constraint Satisfaction Networks, Tony R. Martinez, Xinchuan Zeng

Faculty Publications

This work focuses on improving the Hopfield network for solving optimization problems. Although much work has been done in this area, the performance of the Hopfield network is still not satisfactory in terms of valid convergence and quality of solutions. We address this issue in this work by combing a new activation function (EBA) and a new relaxation procedure (CR) in order to improve the performance of the Hopfield network. Each of EBA and CR has been individually demonstrated capable of substantially improving the performance. The combined approach has been evaluated through 20,000 simulations based on 200 randomly generated city …

Go to article

The Little Neuron That Could, Timothy L. Andersen, Tony R. Martinez Jul 1999

The Little Neuron That Could, Timothy L. Andersen, Tony R. Martinez

Faculty Publications

SLPs (single layer perceptrons) oflen exhibit reasonable generalization performance on many problems of interest. However, due to the well known limitations of SLPs very little effort has been made to improve their performance. This paper proposes a method for improving the performance of SLPs called "wagging" (weight averaging). This method involves training several different SLPs on the same training data, and then averaging their weights to obtain a single SLP. The performance of the wagged SLP is compared with other more complex learning algorithms (bp, c4.5, ibl, MML, etc) on 15 data sets from real world problem domains. Surprisingly, the …

Go to article

A Neural Model Of Centered Tri-Gram Speech Recognition, Tony R. Martinez, Dan A. Ventura, D. Randall Wilson, Brian Moncur Jul 1999

A Neural Model Of Centered Tri-Gram Speech Recognition, Tony R. Martinez, Dan A. Ventura, D. Randall Wilson, Brian Moncur

Faculty Publications

A relaxation network model that includes higher order weight connections is introduced. To demonstrate its utility, the model is applied to the speech recognition domain. Traditional speech recognition systems typically consider only that context preceding the word to be recognized. However, intuition suggests that considering both preceding context as well as following context should improve recognition accuracy. The work described here tests this hypothesis by applying the higher order relaxation network to consider both precedes and follows context in speech recognition. The results demonstrate both the general utility of the higher order relaxation network as well as its improvement over …

Go to article

The Robustness Of Relaxation Rates In Constraint Satisfaction Networks, Tony R. Martinez, Dan A. Ventura, D. Randall Wilson, Brian Moncur Jul 1999

The Robustness Of Relaxation Rates In Constraint Satisfaction Networks, Tony R. Martinez, Dan A. Ventura, D. Randall Wilson, Brian Moncur

Faculty Publications

Constraint satisfaction networks contain nodes that receive weighted evidence from external sources and/or other nodes. A relaxation process allows the activation of nodes to affect neighboring nodes, which in turn can affect their neighbors, allowing information to travel through a network. When doing discrete updates (as in a software implementation of a relaxation network), a goal net or goal activation can be computed in response to the net input into a node, and a relaxation rate can then be used to determine how fast the node moves from its current value to its goal value. An open question was whether …

Go to article

Combining Cross-Validation And Confidence To Measure Fitness, Tony R. Martinez, D. Randall Wilson Jul 1999

Combining Cross-Validation And Confidence To Measure Fitness, Tony R. Martinez, D. Randall Wilson

Faculty Publications

Neural network and machine learning algorithms often have parameters that must be tuned for good performance on a particular task. Leave-one-out cross-validation (LCV) accuracy is often used to measure the fitness of a set of parameter values. However, small changes in parameters often have no effect on LCV accuracy. Many learning algorithms can measure the confidence of a classification decision, but often confidence alone is an inappropriate measure of fitness. This paper proposes a combined measure of Cross- Validation and Confidence (CVC) for obtaining a continuous measure of fitness for sets of parameters in learning algorithms. This paper also proposes …

Go to article

A Comparison Of Eclectic Learning And Stagger, J. Cory Barker, Jargalsaihan Batsaihan Jul 1999

A Comparison Of Eclectic Learning And Stagger, J. Cory Barker, Jargalsaihan Batsaihan

Faculty Publications

This project compares two machine-learning methods, Stagger and Eclectic on their classification correctness. Both systems were tested with real-world data sets previously used and tested in other machine learning and statistical literature. The Eclectic System performed better than Stagger on every data set.

Go to article

First Prev Next Last