Font Size: a A A

Parallel Computation Based Neural Network Approach for Parametric Modeling of Microwave Circuits and Devices

Posted on:2013-12-04Degree:M.A.ScType:Thesis
University:Carleton University (Canada)Candidate:Zhang, ShunluFull Text:PDF
GTID:2458390008979146Subject:Electrical engineering
Abstract/Summary:
This thesis presents a wide-range parametric modeling technique utilizing enhanced Parallel Automatic Data Generation (PADG) and Parallel Multiple ANN Training (PMAT) techniques. A Parallel Model Decomposition (PMD) technique is proposed for neural network models with wide input parameter ranges. In this technique, wide ranges of input parameters are decomposed into small sub-ranges. Multiple neural networks with simple structures, hereby referred as sub-models, are trained to learn the input-output relationship with their corresponding sub-ranges of input parameters. A frequency selection method has been proposed to reduce the sub-models training time and increase the accuracy of sub-models. Once developed, these sub-models cover the entire ranges of parameters and provide an accurate model for microwave components with wide ranges of parameters. A Quasi-Elliptic filter example is used to illustrate the validity of this technique.;The PADG technique and PMAT technique exploit the full utilization of a parallel computational platform that consists of multiple computers with multiple processors. Task distribution strategies have been proposed for both techniques. The proposed techniques have achieved remarkable speed gains against the conventional neural network data generation and training processes. A parallel Back Propagation training implementation using multiple graphics processing units is proposed for the first time. A modular neural network application example has been presented to demonstrate the advantages of PMAT techniques.
Keywords/Search Tags:Neural network, Parallel, Technique, PMAT, Multiple, Training
Related items