Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Neural Supernets: Structuring Artificial Neural Networks According To Cluster Analysis, Simon Lucas Winberg
Neural Supernets: Structuring Artificial Neural Networks According To Cluster Analysis, Simon Lucas Winberg
Masters Theses
A typical feed forward neural network relies solely on its training algorithm, such as backprop or quickprop, to determine suitable weight values for an architecture chosen by the human operator. The architecture itself is typically a fully connected structuring of neurons and synapses where each hidden neuron is connected to every neuron in the next layer. Such architecture does not reflect the structure of the data used to train it. Similarly, in the case where random initial weight values are used, these initial weights are also unlikely to relate to the training set. Thus the job of the training algorithm …
Design And Implementation Of The L-Bone And Logistical Tools, Edward Scott Atchley
Design And Implementation Of The L-Bone And Logistical Tools, Edward Scott Atchley
Masters Theses
The purpose of this paper is to outline the design criteria and implementation of the Logistical Backbone (L-Bone) and the Logistical Tools. These tools, along with IBP and the exNode Library, allow storage to be used as a network resource. These are components of the Network Storage Stack, a design by the Logistical Computing and Internetworking Lab at the University of Tennessee. Having storage as a network resource enables users to do many things that are either difficult or not possible today, such as moving and sharing very large files across administrative domains, improving performance through caching and improving fault-tolerance …
On A Grid-Based Interface To A Special-Purpose Hardware Cluster, Jeanne Marie Lehrter
On A Grid-Based Interface To A Special-Purpose Hardware Cluster, Jeanne Marie Lehrter
Masters Theses
Grid computing is an important and useful tool that enables resource sharing within a computational community. In the grid computing model, each node of the grid is a computational resource that may be used by applications residing on other nodes of the grid or on machines outside of the grid. To make grid computing more accessible to all users, the Innovative Computing Lab on campus at the University of Tennessee has produced a software package called NetSolve. NetSolve is a client-server application that defines interfaces for accessing and utilizing the software and hardware resources of the nodes in the grid …
Design And Simulation Of Self-Organizing Microbial Cellular Automata, Michael Patrick Campfield
Design And Simulation Of Self-Organizing Microbial Cellular Automata, Michael Patrick Campfield
Masters Theses
This paper discusses the design and implementation of cellular automata based on the alteration of genetic sequences in bacteria. The work is composed of five chapters covering the problem, the system’s design, the software simulation of the system and future issues on the problem. The section covering the problem explores the reasons for this work as well as issues that this work solves. The section covering system design details the modified genetic sequences and the algorithm that these sequences implement. The simulation section describes the layout of an experiment along with the test cases experimented on. Finally, the future work …