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
- EP ID EP129556
- DOI -
- Views 109
- Downloads 0
Use of Prefix Trees in Text Error Correction Problem
A deformed fuzzy automaton can be used to calculate similarity value between strings having a nonlimited number of edition errors. In this paper an algorithm is presented that makes use of prefix tree to implement the de...
REAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING
As the problem of urban traffic congestion spreads, there is a pressing need for the introduction of advanced technology and equipment to improve the state-of-the-art of traffic control. Traffic problems nowadays are inc...
An Extended Model Driven Framework for End-to-End Consistent Model Transformation
Model Driven Development (MDD) results in quick transformation from models to corresponding systems. Forward engineering features of modelling tools can help in generating source code from models. To build a robust syste...
A RECENT REVIEW ON ASSOCIATION RULE MINING
Recently more encroachment has emerged in the field of data mining. One of the hottest topic in this area is mining for hidden patterns from the existing massive collection of databases. The knowledge obtained from these...
COMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION
This paper is concerned with the generating an efficient fundamental matrix for image rectification problem under motion. Computation of fundamental matrix is the information source to estimate the accurate optic flow in...