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

STATIC AND DYNAMIC BNP PARALLEL SCHEDULING ALGORITHMS FOR DISTRIBUTED DATABASE

Parallel processing is a technique of executing the multiple tasksconcurrently on different processors. Parallel processing is usedto solve the complex problems that require vast amount ofprocessing time. Task scheduling...

Spline Computation for Solving Magnetohidrodynamics Free Convection Flow

In this paper, we construct numerical algorithms for solving Magnetohidrodynamics(MHD) free convection flow rate whichhas been discussed in detail. It is observed that, for a nonlinear system of differential equation, th...

Finite State Testing and Syntax Testing

This paper is concerned with the testing of the software which is being developed in a structured way. The advantages which accrue from a well-structured or modular organization of software depend upon an ability to inde...

Performance Analysis of Planar Nanocavities-Based Wavelength Demultiplexer for Optical Communication Systems

This paper presents the design and analysis of planar plasmonic wavelength demultiplexer for optical communication systems. The demultiplexer is based on silver-air-silver plasmonic waveguide supported by two nanocavitie...

Scene Oriented Classification of Blurry and Noisy Images Using SVM with Fuzzy C Mean Clustering

Image classification is a challenging task in image processing especially in the case of blurry and noisy images. In this work, we present an extension of scene oriented hierarchical classification of blurry and noisy im...

Download PDF file
  • EP ID EP650625
  • DOI 10.24297/ijct.v13i12.5279
  • Views 93
  • Downloads 0

How To Cite

Ola Mohammed Surakhi, Walid A. Salameh (2014). Enhancing the Performance of the BackPropagation for Deep Neural Network. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 13(12), 5274-5285. https://europub.co.uk/articles/-A-650625