Computer Sciences Commons^™

Automating Construction And Selection Of A Neural Network Using Stochastic Optimization, Jason Lee Hurt

UNLV Theses, Dissertations, Professional Papers, and Capstones

An artificial neural network can be used to solve various statistical problems by approximating a function that provides a mapping from input to output data. No universal method exists for architecting an optimal neural network. Training one with a low error rate is often a manual process requiring the programmer to have specialized knowledge of the domain for the problem at hand.

A distributed architecture is proposed and implemented for generating a neural network capable of solving a particular problem without specialized knowledge of the problem domain. The only knowledge the application needs is a training set that the network …

Consolidated Study On Query Expansion, Abhishek Biruduraju

UNLV Theses, Dissertations, Professional Papers, and Capstones

A typical day of million web users all over the world starts with a simple query. The quest for information on a particular topic drives them to search for it, and in the pursuit of their info the terms they supply for queries varies from person to person depending on the knowledge they have. With a vast collection of documents available on the web universe it is the onus of the retrieval system to return only those documents that are relevant and satisfy the user’s search requirements. The document mismatch problem is resolved by appending extra query terms to the …

Study Of Feature Selection Algorithms For Text-Categorization, Kandarp Dave

UNLV Theses, Dissertations, Professional Papers, and Capstones

This thesis will discuss feature selection algorithms for text-categorization. Feature selection algorithms are very important, as they can make-or-break a categorization engine. The feature selection algorithms that will be discussed in this thesis are Document Frequency, Information Gain, Chi Squared, Mutual Information, NGL (Ng-Goh-Low) coefficient, and GSS (Galavotti-Sebastiani-Simi) coefficient . The general idea of any feature selection algorithm is to determine importance of words using some measure that can keep informative words, and remove non-informative words, which can then help the text-categorization engine categorize a document, D , into some category, C . These feature selection methods are explained, implemented, …

Processj: A Process-Oriented Programming Language, Matthew Sowders

UNLV Theses, Dissertations, Professional Papers, and Capstones

Java is a general purpose object-oriented programming language that has been widely adopted. Because of its high adoption rate and its lineage as a C-style language, its syntax is familiar to many programmers. The downside is that Java is not natively concurrent. Volumes have been written about concurrent programming in Java; however, concurrent programming is difficult to reason about within an object-oriented paradigm and so is difficult to get right.

occam -π is a general purpose process-oriented programming language. Concurrency is part of the theoretical underpinnings of the language. Concurrency is simple to reason about within an occam -π application …

Improved Algorithms For Ear-Clipping Triangulation, Bartosz Kajak

UNLV Theses, Dissertations, Professional Papers, and Capstones

We consider the problem of improving ear-slicing algorithm for triangulating a simple polygon. We propose two variations of ear-slicing technique for generating “good-quality” triangulation. The first approach is based on searching for the best triangle along the boundary. The second approach considers polygon partitioning on a pre-process before applying the ear-slicing. Experimental investigation reveals that both approaches yield better quality triangulation than the standard ear-slicing method.