Enhancing the Performance of the BackPropagation for Deep Neural Network
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2014, Vol 13, Issue 12
Abstract
The standard Backpropagation Neural Network (BPNN) Algorithm is widely used in solving many real problems in world. But the backpropagation suffers from different difficulties such as the slow convergence and convergence to local minima. Many modifications have been proposed to improve the performance of the algorithm such as careful selection of initial weights and biases, learning rate, momentum, network topology and activation function. This paper will illustrate a new additional version of the Backpropagation algorithm. In fact, the new modification has been done on the error signal function by using deep neural networks with more than one hidden layers. Experiments have been made to compare and 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 has improved the classical Bp in terms of its efficiency.
Authors and Affiliations
Ola Mohammed Surakhi, Walid A. Salameh
Keywords
Related Articles
- EP ID EP650625
- DOI 10.24297/ijct.v13i12.5279
- Views 92
- Downloads 0
Mapping between XML and RDF via DTD
XML has gained massive popularity for representation of data in last decades. Both HTML and XML are used as primary data formats since the existence of World Wide Web. As the amount of data is growing, need has emerged t...
A NOVEL APPROACH OF CLUSTERING FOR ENHANCED LIFETIME IN WIRELESS SENSOR NETWORK
Wireless sensor network has revolutionized the way computing and software services are delivered to the clients on demand. Our research work proposed a new method for cluster head selection having less computational comp...
A REVIEW ON RESOURCE ALLOCATION MECHANISM IN CLOUD ENVIORNMENT
Cloud computing is Internet based development and use of computer technology. It is a style of computing in which dynamically scalable and often virtualized resources are provided as a service over the Internet. Users ne...
Morphology of Koch Fractal Antenna
Antenna is paramount element for the radio communication entity using radio frequency and microwaves. In twenty-first century wireless communication systems, there is a demand for wider bandwidth, multiband and low pro...
A REVIEW ON A HYBRID APPROACH USING MOBILE SINK AND FUZZY LOGIC FOR REGION BASED CLUSTERING IN WSN
A Wireless Sensor Network or WSN is supposed to be made up of a large number of sensors and at least one base station. The sensors are autonomous small devices with several constraints like the battery power, computation...