Efficient training of backpropagation neural networks
Dissertant
Otair, Muhammad Abd Allah Arif
Thesis advisor
Comitee Members
Isa, Ghassan Farid
al-Shammari, Husayn Hadi Uwayyid
Abu al-Suud, Salih Mustafa
University
Arab Academy for Financial and Banking Sciences
Faculty
The Faculty of Information Systems and Technology
University Country
Jordan
Degree
Ph.D.
Degree Date
2004
English Abstract
Since the discovery of the Backpropagation algorithm, many modified and new algorithms have been proposed for training of feedforward neural networks.
The problem with slow convergence rate has, however, not been solved when the training is on large-scale problems.
There is still a need for more efficient algorithms.
This Ph.D.
thesis describes different approaches to improve the convergence rate.
The target of this thesis is to discover an Optical Backpropagation (OBP) and the stochastic version of this algorithm.
Other important results are the modifying of existing algorithms that use Backpropagation to achieve better results in versions of different parameters selection.
The OBP algorithm proposes a modified error function to reduce the probability that output nodes are near the wrong extreme value of sigmoid activation function.
This is acquired through a strong error signal for the incorrectly saturated output node and a weak error signal for the correctly saturated output node.
The weak error signal for the correctly saturated output node, also, prevents overspecialization of learning for training patterns.
The major contributions of this thesis are the design and utilization of the OBP algorithm for improving the performance of current supervised training algorithms on different experiments.
These improvements include reduction of the training time for some existing supervised training algorithms (such as backpropagation, Backpropagation with Momentum and Delta-Bar-Delta).
Further, the experimental results show that the OBP algorithm converges to a reasonable range of error after a few number of training epochs, making it suitable for dynamic real-time applications.
Main Subjects
Information Technology and Computer Science
Topics
No. of Pages
195
Table of Contents
Table of contents.
Abstract.
Chapter one : Artificial neural networks.
Chapter two : Backprbpagationneural networks.
Chapter three : Modified versions of the backpropagation algorithm.
Chapter four : The optical backpropagation algorithm.
Chapter five : Experimental evaluation.
Chapter six : Conclusion.
References.
American Psychological Association (APA)
Otair, Muhammad Abd Allah Arif. (2004). Efficient training of backpropagation neural networks. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences, Jordan
https://search.emarefa.net/detail/BIM-304755
Modern Language Association (MLA)
Otair, Muhammad Abd Allah Arif. Efficient training of backpropagation neural networks. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences. (2004).
https://search.emarefa.net/detail/BIM-304755
American Medical Association (AMA)
Otair, Muhammad Abd Allah Arif. (2004). Efficient training of backpropagation neural networks. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences, Jordan
https://search.emarefa.net/detail/BIM-304755
Language
English
Data Type
Arab Theses
Record ID
BIM-304755
