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 152
- Downloads 0
A STUDY OF INTELLIGENT CONTROLLERS APPLICATION IN DISTRIBUTED SYSTEMS
Intelligent Control emulates the human intelligence and achieves automation in various areas of Engineering. Intelligent Controls have been used mainly in the areas of Electrical Systems; Machine Intelligence based syste...
IMPACT OF ICT ON PRIME INSTITUTES OF DELHI
The premise of the present study is to ascertain that whether the libraries of prime institutes in Delhi are benefitted with the advent of Information and Communication Technology (ICT) based products and services. Idea...
TAXONOMY CONSTRUCTION TECHNIQUES – ISSUES AND CHALLENGES
For any information to be organized, taxonomy is essential. Taxonomy plays a very important role for information and content management. Also it helps in searching of content. The most common method for constructing taxo...
RELATIVE QUERY RESULTS RANKING FOR ONLINE USERS IN WEB DATABASES
To handle with the problem of so many-answers replied from an online Web database in response to a relative query, this paper proposes a unique approach to rank the similar query results. Depending upon the on the databa...
An Implementation of Integer Programming Techniques in Clustering Algorithm
This paper mainly deals with the analysis of IPP in clustering. Clustering is exemplified by the unsupervised learning of patterns and clusters that may exist in a given database and is a useful tool for Knowledge Discov...