Forward only counter propagation network for balance scale weight & distance classification task

This paper proposes the forward only counter propagation network (FOCPN) for solving the Balance Scale Weight & Distance (BSWD) classification task. Balance Scale Weight & Distance application is used for the psychological experiments and it is one of the challenging jobs. The forward only c...

Full description

Saved in:
Bibliographic Details
Main Authors: Bangyal, W. H., Ahmad, J., Shafi, I., Abbas, Q.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Artificial neural networks
FOCPN
learning rate
Neurons
Radiation detectors
SOM
Training
Unsupervised learning
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes the forward only counter propagation network (FOCPN) for solving the Balance Scale Weight & Distance (BSWD) classification task. Balance Scale Weight & Distance application is used for the psychological experiments and it is one of the challenging jobs. The forward only counter propagation network (FOCPN) has the architecture consisting of three layers as the input layer, the middle (kohonen) and the output layer and having different learning rule The Experiments are performed on different radius of the neighborhood and learning rate based on size of the map. Experimental results show that the forward only counter propagation network (FOCPN's) convergence is faster and it gives the improved learning efficiency and reliable prediction performance. Also, the classification accuracy is much higher than the other models used for this purpose.
DOI:10.1109/NaBIC.2011.6089615