Design and Implementation of Binary Neural Network Classification Learning Algorithm

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2012, Vol 1, Issue 6

Abstract

 In this paper a Binary Neural Network Learning (BNN-CLA)[1] is analyzed and implemented for solving multi class problem normally the classifier are construct by combining the outputs of several binary ones. The BNNC offers high degree of parallelism in hidden layer formation for all multiple classes to reduce the time for learning. The learning method is an iterative process to optimize the classifier parameters. In this approach, overlapping problem is tackled to enhance the performance of classifier by changing hyper-sphere radius. Exhaustive testing is carried out. Accuracies and number of neuron are evaluated and compare with BNNC[4]. The method have been tested on Fisher's well known Iris data data set and experimental result shown the classification ability improved by using FCLA algorithm. While comparing with BNNC[4] in most cases accuracies improved in BNNL because of elimination of samples which are lying in overlapping region of classes. Thus tacking overlapping issue improved performance of this classifier.

Authors and Affiliations

Shweta Kori

Keywords

Related Articles

 Software Development Effort and Cost Estimation: Neuro-Fuzzy Model

 Software development effort and cost prediction is one of the important activities in software project management. Accuracy in prediction is a challenge for software developers. There are many models exists that...

 An Overview of TRIZ Problem-Solving Methodology and its  Applications

 TRIZ, which is a Russian word that stands for “Theory of Inventive Problem Solving”, is a problemsolving methodology that was invented based on the belief that there are universal principles of invention that &nbsp...

 A Comparative Study between Time Series and Neural Networkfor Exchange Rate Forecasting

 Abstract: Exchange rate forecasting has become a new research topic in present time for best market strategy,planning of investment for investor in foreign project and also for business profit. The methods or proce...

 The Cyberspace: Redefining A New World

Abstract: The cyberspace driven by information systems and the Internet is transforming our environment inextraordinary ways by enabling economic growth and providing new means by which people connect, interactand collab...

Simulation of Parallel and Distributed Computing: A Review

Abstract : Parallel and Distributed Computing has made it possible to simulate large infrastructures like Telecom networks, air traffic etc. in an easy and effective way. It not only makes the processes faster and reliab...

Download PDF file
  • EP ID EP93338
  • DOI -
  • Views 90
  • Downloads 0

How To Cite

Shweta Kori (2012).  Design and Implementation of Binary Neural Network Classification Learning Algorithm. IOSR Journals (IOSR Journal of Computer Engineering), 1(6), 36-42. https://europub.co.uk/articles/-A-93338