Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm

Algoritma perambatan balik telah terbukti sebagai salah satu algoritma rangkaian neural yang paling berjaya. Namun demikian, seperti kebanyakan kaedah pengoptimuman yang berasaskan kecerunan, ianya menumpu dengan lamb at dan keupayaannya berkurangan bagi tugas-tugas yang lebih besar dan kompleks....

Description complète

Détails bibliographiques
Auteur principal: Zainuddin, Zarita
Format: Thèse
Langue:anglais
Publié: 2001
Sujets:
Accès en ligne:http://eprints.usm.my/31464/
Abstract Abstract here
_version_ 1855629457138647040
author Zainuddin, Zarita
author_facet Zainuddin, Zarita
author_sort Zainuddin, Zarita
description Algoritma perambatan balik telah terbukti sebagai salah satu algoritma rangkaian neural yang paling berjaya. Namun demikian, seperti kebanyakan kaedah pengoptimuman yang berasaskan kecerunan, ianya menumpu dengan lamb at dan keupayaannya berkurangan bagi tugas-tugas yang lebih besar dan kompleks. Dalam tesis ini, faktor-faktor yang menguasai kepantasan pembelajaran algoritma perambatan balik diselidik dan dianalisa secara matematik untuk membangunkan strategi-strategi bagi memperbaiki prestasi algoritma pembelajaran rangkaian neural ini. Faktor-faktor ini meliputi pilihan pemberat awal, pilihan fungsi pengaktifan dan nilai sasaran serta dua parameter perambatan, iaitu kadar pembelajaran dan faktor momentum. The backpropagation algorithm has proven to be one of the most successful neural network learning algorithms. However, as with many gradient based optimization methods, it converges slowly and it scales up poorly as tasks become larger and more complex. In this thesis, factors that govern the learning speed of the backpropagation algorithm are investigated and mathematically analyzed in order to develop strategies to improve the performance of this neural network learning algorithm. These factors include the choice of initial weights, the choice of activation function and target values, and the two backpropagation parameters, the learning rate and the momentum factor.
first_indexed 2025-10-17T08:07:54Z
format Thesis
id usm-31464
institution Universiti Sains Malaysia
language English
last_indexed 2025-10-17T08:07:54Z
publishDate 2001
record_format EPrints
record_pdf Restricted
spelling usm-314642017-01-06T07:49:22Z http://eprints.usm.my/31464/ Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm Zainuddin, Zarita QA1-939 Mathematics Algoritma perambatan balik telah terbukti sebagai salah satu algoritma rangkaian neural yang paling berjaya. Namun demikian, seperti kebanyakan kaedah pengoptimuman yang berasaskan kecerunan, ianya menumpu dengan lamb at dan keupayaannya berkurangan bagi tugas-tugas yang lebih besar dan kompleks. Dalam tesis ini, faktor-faktor yang menguasai kepantasan pembelajaran algoritma perambatan balik diselidik dan dianalisa secara matematik untuk membangunkan strategi-strategi bagi memperbaiki prestasi algoritma pembelajaran rangkaian neural ini. Faktor-faktor ini meliputi pilihan pemberat awal, pilihan fungsi pengaktifan dan nilai sasaran serta dua parameter perambatan, iaitu kadar pembelajaran dan faktor momentum. The backpropagation algorithm has proven to be one of the most successful neural network learning algorithms. However, as with many gradient based optimization methods, it converges slowly and it scales up poorly as tasks become larger and more complex. In this thesis, factors that govern the learning speed of the backpropagation algorithm are investigated and mathematically analyzed in order to develop strategies to improve the performance of this neural network learning algorithm. These factors include the choice of initial weights, the choice of activation function and target values, and the two backpropagation parameters, the learning rate and the momentum factor. 2001-06 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/31464/1/ZARITA_ZAINUDDIN.pdf Zainuddin, Zarita (2001) Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm. PhD thesis, Universiti Sains Malaysia.
spellingShingle QA1-939 Mathematics
Zainuddin, Zarita
Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
thesis_level PhD
title Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
title_full Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
title_fullStr Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
title_full_unstemmed Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
title_short Acceleration Strategies For The Backpropagation Neural Network Learning Algorithm
title_sort acceleration strategies for the backpropagation neural network learning algorithm
topic QA1-939 Mathematics
url http://eprints.usm.my/31464/
work_keys_str_mv AT zainuddinzarita accelerationstrategiesforthebackpropagationneuralnetworklearningalgorithm