Enhancing the Performance of the BackPropagation for Deep Neural Network
Journal: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY (Vol.13, No. 12)Publication Date: 2014-10-31
Authors : Ola Mohammed Surakhi; Walid A. Salameh;
Page : 5274-5285
Keywords : Neural Networks; Deep Neural Network; Backpropagation; Momentum; learning Rate; Optical Backpropagation; Extended Optical Bp; performance analysis;
Abstract
The standard Backpropagation NeuralNetwork (BPNN) Algorithm is widely used insolving many real problems in world. But thebackpropagation suffers from different difficultiessuch as the slow convergence and convergence tolocal minima. Many modifications have beenproposed to improve the performance of thealgorithm such as careful selection of initial weightsand biases, learning rate, momentum, networktopology and activation function. This paper willillustrate a new additional version of theBackpropagation algorithm. In fact, the newmodification has been done on the error signalfunction by using deep neural networks with morethan one hidden layers. Experiments have beenmade to compare and evaluate the convergencebehavior of these training algorithms with twotraining problems: XOR, and the Iris plantclassification. The results showed that the proposedalgorithm has improved the classical Bp in terms ofits efficiency.
Other Latest Articles
- Proposing a method based on Ants algorithm for optimizing energy consumption and routing in wireless sensor networks
- Design of BPSK Modulator Using VHDL
- A Proposed Electronic Health Record Content Structure According To Several Clinical Organizations Survey
- Validation of DeLone and McLean model to analyze decision support systems success in the banking sector of Oman
- Microprocessor Architecture Era for Development Cloud Computing of Ministry of Electricity and Energy of Egypt
Last modified: 2016-06-29 16:40:03