A COMPARISON OF CONSTRUCTIVE AND PRUNING ALGORITHMS TO DESIGN NEURAL NETWORKS

Journal Title: Indian Journal of Computer Science and Engineering - Year 2011, Vol 2, Issue 3

Abstract

This paper presents a comparison between constructive and pruning algorithms to design Neural Network (NN). Both algorithms have advantages as well as drawbacks while designing the architecture of NN. Constructive algorithm is computationally economic because it simply specifies straightforward initial NN architecture. Whereas the large initial NN size of pruning algorithm allows reasonably quick learning with reduced complexity. Two popular ideas from two categories: “cascade-correlation [1]” from constructive algorithms and “skeletonization [2]” from pruning algorithms are chosen here. They have been tested on several benchmark problems in machine learning and NNs. These are the cancer, the credit card, the heart disease, the thyroid and the soybean problems. The simulation results show the number of iterations during the training period and the generalization ability of NNs designed by using these algorithms for these problems.

Authors and Affiliations

KAZI MD. ROKIBUL ALAM , BIKASH CHANDRA KARMOKAR , MD. KIBRIA SIDDIQUEE

Keywords

Related Articles

HOME BASED WELLNESS MONITORING SYSTEM THROUGH MEMS TECHNOLOGY

A new generation of massive-scale sensor networks suitable for a range of commercial and military applications is brought forth by advances in MEMS (micro electro mechanical system technology).Accordingly Wirelesssensor-...

COMPARISON AND EVALUATION ON METRICS BASED APPROACH FOR DETECTING CODE CLONE

Many techniques were proposed for detecting code clone. In this paper we have compared the metrics based on speed, quality and their cost as these are the most that affects due to code clone. The strength and weakness of...

Searching SNT in XML Documents Using Reduction Factor

XML has become the most popular standard for data representation. In XML standard the documents represented as rooted ordered trees. The efficient query processing can be performed on the labeled document structure. The...

AN IMPLEMENTATION OF PACMAN GAME USING ROBOTS

As the field of robotics are advancing, robotics education needs to consider technological advances and societal level of interest. Realizing computer games in robotic platforms is one such technological advance for educ...

APPLYING PARALLEL ASSOCIATION RULE MINING TO HETEROGENEOUS ENVIRONMENT

The work aims to discover frequent patterns by generating the candidates and frame the association rules after which filter out only the efficient rules based on various Rule Interestingness measures. As all these requir...

Download PDF file
  • EP ID EP129556
  • DOI -
  • Views 143
  • Downloads 0

How To Cite

KAZI MD. ROKIBUL ALAM, BIKASH CHANDRA KARMOKAR, MD. KIBRIA SIDDIQUEE (2011). A COMPARISON OF CONSTRUCTIVE AND PRUNING ALGORITHMS TO DESIGN NEURAL NETWORKS. Indian Journal of Computer Science and Engineering, 2(3), 486-491. https://europub.co.uk./articles/-A-129556