Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Entire DC Network
Efficient Mapping Of Neural Network Models On A Class Of Parallel Architectures., Behnam Seyed Arad
Efficient Mapping Of Neural Network Models On A Class Of Parallel Architectures., Behnam Seyed Arad
LSU Historical Dissertations and Theses
This dissertation develops a formal and systematic methodology for efficient mapping of several contemporary artificial neural network (ANN) models on k-ary n-cube parallel architectures (KNC's). We apply the general mapping to several important ANN models including feedforward ANN's trained with backpropagation algorithm, radial basis function networks, cascade correlation learning, and adaptive resonance theory networks. Our approach utilizes a parallel task graph representing concurrent operations of the ANN model during training. The mapping of the ANN is performed in two steps. First, the parallel task graph of the ANN is mapped to a virtual KNC of compatible dimensionality. This involves decomposing …
Land/Water Interface Delineation Using Neural Networks., Rajabhushanam Cherukuri
Land/Water Interface Delineation Using Neural Networks., Rajabhushanam Cherukuri
LSU Historical Dissertations and Theses
The rapid decline in acreage of land areas in wetlands caused by frequent inundations and flooding has brought about an increased awareness and emphasis on the identification and inventory of land and water areas. This dissertation evaluates three classification methods--Normalized Difference Vegetation Index technique, Artificial Neural Networks, and Maximum-Likelihood classifier for the delineation of land/water interface conditions using Landsat-TM imagery. The effects of three scaling algorithms, including resampling by aggregation, Gaussian smoothing, and local variance analysis, on the classification accuracy are analyzed to determine how the delineation, quantification and analysis of land/water boundaries relate to problems of mixed pixels, scale …
Stochastic Techniques For The Solution Of Electrostatic Problems With Applications To Electron Optics., Elias Kougianos
Stochastic Techniques For The Solution Of Electrostatic Problems With Applications To Electron Optics., Elias Kougianos
LSU Historical Dissertations and Theses
We apply stochastic techniques towards the solution of the two-dimensional Laplace's equation in boundary value problems encountered in the calculation of electrostatic potentials in electron lenses and deflectors. The justification of these techniques arises from an astonishingly simple but far-reaching principle, which has been known for a long time but has been rarely used: the potential at any point in the interior of a charge-free region can be calculated by performing random walks starting at this point and terminating at the boundary of the region--the potential is then the average of the potential boundary values (assumed known) over the random …
Design And Analysis Of Optical Interconnection Networks For Parallel Computation., Yueming Li
Design And Analysis Of Optical Interconnection Networks For Parallel Computation., Yueming Li
LSU Historical Dissertations and Theses
In this doctoral research, we propose several novel protocols and topologies for the interconnection of massively parallel processors. These new technologies achieve considerable improvements in system performance and structure simplicity. Currently, synchronous protocols are used in optical TDM buses. The major disadvantage of a synchronous protocol is the waste of packet slots. To offset this inherent drawback of synchronous TDM, a pipelined asynchronous TDM optical bus is proposed. The simulation results show that the performance of the proposed bus is significantly better than that of known pipelined synchronous TDM optical buses. Practically, the computation power of the plain TDM protocol …
Traffic Management And Congestion Control In The Atm Network Model., Sundararajan Vedantham
Traffic Management And Congestion Control In The Atm Network Model., Sundararajan Vedantham
LSU Historical Dissertations and Theses
Asynchronous Transfer Mode (ATM) networking technology has been chosen by the International Telegraph and Telephony Consultative Committee (CCITT) for use on future local as well as wide area networks to handle traffic types of a wide range. It is a cell based network architecture that resembles circuit switched networks, providing Quality of Service (QoS) guarantees not normally found on data networks. Although the specifications for the architecture have been continuously evolving, traffic congestion management techniques for ATM networks have not been very well defined yet. This thesis studies the traffic management problem in detail, provides some theoretical understanding and presents …