ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Extraction of Classification Rules from Trained ANN for Multiclass Data?

Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.3, No. 5)

Publication Date:

Authors : ; ;

Page : 776-779

Keywords : Decision tree; Artificial Neural Network; Rule Extraction methods; Multiclass Data;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

In Data mining classification rules are generated using some classification methods. One of the most common methods for rule generation is Decision tree which refers supervised learning. After generating classification rules we can apply those rules on unknown data and reach to the results. Artificial Neural Network is one kind of network that has the ability to learn and thereby acquire knowledge and make it available for use. But ANN gives results of only trained data. Unseen samples can be classified by ANN but nobody can understand how that classification was made. All training is inside the ANN in the form of weights. So we require to extract that training (knowledge) in form of rules. Classification rules are generated from trained ANN for multi-class dataset by Rule Extraction methods. So during the phase of testing classification rules give results of testing data.

Last modified: 2014-05-27 21:18:57