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 97
- Downloads 0
Estimation of Performance Improvement Derived from TCP/IP Offload Engine with Software Emulation
Many TOE (TCP/IP Offload Engine) devices have been developed and installed in high-end systems. Although there have been many analysis of the effectiveness of TOE devices, there remain open issues related to them. Fo...
Localization of Sensor Nodes using Flooding in Wireless Sensor Networks
The accuracy of localization is a significant criterion to evaluate the practical utility of localization algorithm in wireless sensor networks (WSN). In mostly localization algorithms, one of the main methods to improve...
Performance Evaluation System for Decision Tree Algorithms
In the machine learning process, classification can be described by supervise learning algorithm. Classification techniques have properties that enable the representation of structures that reflect knowledge of the domai...
Fuzzy Mean Point Clustering using K-means algorithm for implementing the movecentroid function code
The paper focus on combination of K-Means algorithm for Fuzzy Mean Point Clustering Neural Network (FMPCNN). The algorithm is implemented in JAVA program code for implementing the movecentroid function code into FMPCNN.Â...
Optimum Space Utilization Approach to Improve Persistence of WSNs
Wireless Sensor Networks (WSNs) are consists of huge number of sensor nodes, restricted with limited power, Â for provide services with cooperation to sense data and send to server. Various routing techniques are introdu...