Class Label Prediction using Back Propagation Algorithm: A comparative study with and without Thresholds (Bias)

Authors

  • NV Saiteja Reddy Department of CSE, GITAM University, Visakhapatnam, Andhra Pradesh, India
  • Srikanth Department of CSE, GITAM University, Visakhapatnam, Andhra Pradesh, India

Keywords:

Back Propagation Algorithm, Neural Network, Programming Neural Networks

Abstract

The Back propagation Algorithm is a multilayered, feed forward neural network and is one of the most popular and efficient techniques used. This can be used for dataset classification with suitable combination of training, learning and transfer functions. However, there are some problems associated with this Algorithm like Step-size Problem and Local Minima. In this paper we will discuss about the working of the algorithm and efficient ways to perform learning by overcoming the problems in it. We use three common classification problems to illustrate the ways of efficient learning. All the methods and algorithms were implemented using the features of Java.

References

. Breast Cancer Wisconsin (Original) Dataset - https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Original%29

. Iris Data Set:https://archive.ics.uci.edu/ml/datasets/Iris

. T. Lalis, B. D. Gerardo and Y. Byun (2014). “An Adaptive Stopping Criterion for Backpropagation Learning in Feedforward Neural Network”. International Journal of Multimedia and Ubiquitous Engineering Vol.9, No. 8, pp. 149-156

. JeffHeaton (2005). “Programming Neural Networks in Java”. Heaton Research

. Saurabh Karsoliya (2012). “Approximating Number of Hidden layer neurons in MultipleHidden Layer BPNN Architecture”. International Journal of Engineering Trends and Technology-Volume3 Issue6

. Tom M. Mitchell (1997). “Machine Learning”. McGraw Hill

. Wouter F. Schmidt, Martin A. Kraaijveld and Robert P.W. Duin (1992). “Feed Forward Neural Networks With Random Weights”- Proceedings. 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems

. Wine Data Set - https://archive.ics.uci.edu/ml/datasets/Wine

Downloads

Published

2025-11-10

How to Cite

[1]
N. Saiteja Reddy and T. Srikanth, “Class Label Prediction using Back Propagation Algorithm: A comparative study with and without Thresholds (Bias)”, Int. J. Comp. Sci. Eng., vol. 3, no. 7, pp. 65–70, Nov. 2025.

Issue

Vol. 3 No. 7 (2015): IJCSE July Edition

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.