The Application of Genetic Algorithms to Artificial Neural Networks
碩士 === 國立成功大學 === 航空太空工程學系 === 88 === The objective of this research is to apply GA(Genetic Algorithms) to the learning of ANN(Artificial Neural Network). When the network structure has been determined, the capability of a particular ANN depends on the learning rule it adapts. One of the most commo...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2000
|
Online Access: | http://ndltd.ncl.edu.tw/handle/39295925844029378815 |
id |
ndltd-TW-088NCKU0295052 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-088NCKU02950522015-10-13T10:57:07Z http://ndltd.ncl.edu.tw/handle/39295925844029378815 The Application of Genetic Algorithms to Artificial Neural Networks 基因演算法於類神經網路之應用 Jyh-Iuan Sheu 許智淵 碩士 國立成功大學 航空太空工程學系 88 The objective of this research is to apply GA(Genetic Algorithms) to the learning of ANN(Artificial Neural Network). When the network structure has been determined, the capability of a particular ANN depends on the learning rule it adapts. One of the most commonly used learning rule is the Back Propagation(BP) method. It is well known that BP is a steepest descent method that relies on the system gradient. It does not guarautee to reach the system global optimal. On the other hand, Genetic Algorithms(GA) are based on the simulation of natural evolution process. It follows the Darwin''s principal of "Survival of the fittest", which always searchs for the global optimal under the system constraint. In this steady, a hybird method of BP and GA will be developed to imrove the robustness of learning rule for ANN. Dartzi Pan 潘大知 2000 學位論文 ; thesis 77 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 航空太空工程學系 === 88 === The objective of this research is to apply GA(Genetic Algorithms) to the learning of ANN(Artificial Neural Network). When the network structure has been determined, the capability of a particular ANN depends on the learning rule it adapts. One of the most commonly used learning rule is the Back Propagation(BP) method. It is well known that BP is a steepest descent method that relies on the system gradient. It does not guarautee to reach the system global optimal. On the other hand, Genetic Algorithms(GA) are based on the simulation of natural evolution process. It follows the Darwin''s principal of "Survival of the fittest", which always searchs for the global optimal under the system constraint. In this steady, a hybird method of BP and GA will be developed to imrove the robustness of learning rule for ANN.
|
author2 |
Dartzi Pan |
author_facet |
Dartzi Pan Jyh-Iuan Sheu 許智淵 |
author |
Jyh-Iuan Sheu 許智淵 |
spellingShingle |
Jyh-Iuan Sheu 許智淵 The Application of Genetic Algorithms to Artificial Neural Networks |
author_sort |
Jyh-Iuan Sheu |
title |
The Application of Genetic Algorithms to Artificial Neural Networks |
title_short |
The Application of Genetic Algorithms to Artificial Neural Networks |
title_full |
The Application of Genetic Algorithms to Artificial Neural Networks |
title_fullStr |
The Application of Genetic Algorithms to Artificial Neural Networks |
title_full_unstemmed |
The Application of Genetic Algorithms to Artificial Neural Networks |
title_sort |
application of genetic algorithms to artificial neural networks |
publishDate |
2000 |
url |
http://ndltd.ncl.edu.tw/handle/39295925844029378815 |
work_keys_str_mv |
AT jyhiuansheu theapplicationofgeneticalgorithmstoartificialneuralnetworks AT xǔzhìyuān theapplicationofgeneticalgorithmstoartificialneuralnetworks AT jyhiuansheu jīyīnyǎnsuànfǎyúlèishénjīngwǎnglùzhīyīngyòng AT xǔzhìyuān jīyīnyǎnsuànfǎyúlèishénjīngwǎnglùzhīyīngyòng AT jyhiuansheu applicationofgeneticalgorithmstoartificialneuralnetworks AT xǔzhìyuān applicationofgeneticalgorithmstoartificialneuralnetworks |
_version_ |
1716834708560543744 |