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
- EP ID EP93338
- DOI -
- Views 112
- Downloads 0
Persuasive Cued Click Based Graphical Password with Scrambling For Knowledge Based Authentication Technique with Image Scrambling
Adequate user authentication is a persistent problem, particularly with hand- held devices such as Personal Digital Assistants (PDAs), which tend to be highly personal and at the fringes of an organization’s &nb...
Image Reconstruction of Tumor Brain Cells
Image reconstruction techniques are used to create 2-D and 3-D images from sets of 1-D projections. These reconstruction techniques form the basis for common imaging modalities such as CT, MRI, and PET, and they are usef...
Detecting Good Neighbor Nodes and Finding Reliable Routing Path Based on AODV Protocol
Wireless operations allow services, such as long-range communications, that are impossible or impractical to implement with the use of wires. It is supported by well-liked technique known as Adhoc Protocol  ...
DIP Using Image Encryption and XOR Operation AffineTransform
Abstract: Digital image processing is the use of computer algorithms to perform image processing on digitalimages. It is a subfield of digital signal processing. Digital image processing has many advantages over an...
Network Lifespan Maximization For Wireless Sensor Networks Using Nature-Inspired Elephant Based Swarm Optimization
: The robust and complex real-time applications and dramatically increased sensor capabilities may play a vital role in enhancing the lifespan of WSNs. On the other hand majority of WSNs operate on battery powe...