Enhancing the performance of the back propagation algorithm for deep neural network
Other Title(s)
تحسين أداء خوارزمية الانتشار الخلفي في الخلايا العصبية الصناعية
Dissertant
Thesis advisor
Comitee Members
Umar, Khamis
Ghnimat, Rawan
al-Dawud, Ali Sad
University
Princess Sumaya University for Technology
Faculty
King Hussein Faculty for Computing Sciences
Department
Department of Computer Sciences
University Country
Jordan
Degree
Master
Degree Date
2014
English Abstract
One major problem encountered by researchers in improving the performance of the Backpropagation algorithm is the slow convergence and convergence to the local minima.
Many modified and new versions on the Backpropagation since it has been used and launched.
Those have proposed a careful selection on the initial weights and biases, learning rate, momentum, network topology and activation function.
As the algorithm is widely used in solving many real problems in the world there is still a sever need for more efficient modification.
This thesis, in fact, will describe a new approach to enhance the performance of training multi-layer neural networks and deep neural networks with more than one hidden layer by using a new algorithm which is called the Extended Optical Backpropagation (EOBP).
A new error function has been adopted to replace the error function used in Optical Backpropagation OBP algorithm which gives a rapid reaction to changes in the weights value by increasing the training speed with less number of iterations and without loss of learn-ability.
Experiments have been conducted to compare and to evaluate the convergence behavior of these training algorithms with two training problems: XOR and the Iris plant classification.
The results showed that the proposed algorithm converges to a reasonable range of error after a few numbers of training epochs
Main Subjects
Topics
No. of Pages
67
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Artificial neural network.
Chapter Three : The proposed algorithm.
Chapter Four : Experimental evaluation.
Chapter Five : Conclusions.
References.
American Psychological Association (APA)
Surakhi, Ula Muhammad. (2014). Enhancing the performance of the back propagation algorithm for deep neural network. (Master's theses Theses and Dissertations Master). Jordan
https://search.emarefa.net/detail/BIM-535254
Modern Language Association (MLA)
Surakhi, Ula Muhammad. Enhancing the performance of the back propagation algorithm for deep neural network. (Master's theses Theses and Dissertations Master). (2014).
https://search.emarefa.net/detail/BIM-535254
American Medical Association (AMA)
Surakhi, Ula Muhammad. (2014). Enhancing the performance of the back propagation algorithm for deep neural network. (Master's theses Theses and Dissertations Master). Jordan
https://search.emarefa.net/detail/BIM-535254
Language
English
Data Type
Arab Theses
Record ID
BIM-535254