Scientific Research and Essays

  • Abbreviation: Sci. Res. Essays
  • Language: English
  • ISSN: 1992-2248
  • DOI: 10.5897/SRE
  • Start Year: 2006
  • Published Articles: 2748

Full Length Research Paper

Visualization analysis of feed forward neural network input contribution

Jamal Alsakran
  • Jamal Alsakran
  • The University of Jordan, Amman, Jordan.
  • Google Scholar
Ali Rodan
  • Ali Rodan
  • The University of Jordan, Amman, Jordan.
  • Google Scholar
Nouh Alhindawi
  • Nouh Alhindawi
  • Jadara University, Irbid 21110, Jordan.
  • Google Scholar
Hossam Faris
  • Hossam Faris
  • The University of Jordan, Amman, Jordan.
  • Google Scholar


  •  Received: 31 March 2014
  •  Accepted: 01 July 2014
  •  Published: 30 July 2014

Abstract

The complexity of domain problem can slow or even hinder the learning process of neural networks. It is rather difficult to overcome such an obstacle because neural networks, as cited today in the literature, lack the interpretability of their internal structures. In this paper, we present a visualization approach capable of enhancing the understanding of neural networks. Our approach visualizes input and weight contributions, sensitivity analysis, and provides guidance in pruning less influential features and consequently reducing the complexity of domain problem while maintaining acceptable error rates. We conduct experiments on various datasets to show the effectiveness of our approach.

 

Key words: Neural network, visualization, input contribution, sensitivity analysis