Abstract
The paper discusses the experiments performed with Machine Learning algorithms (ID3, C4.5, Bagged-C4.5, Boosted-C4.5 and Naive Bayes) and an algorithm made on the basis of a combination of genetic algorithms (GA) and ID3. The latter algorithm is implemented as an extension of the MLC++ Library of Stanford University. The behaviour of the algorithm is tested using 24 databases including those with a large number of attributes. It is shown that owing to “hill-climbing” problem solving, the characteristics of the classifier made with the help of the new algorithm became significantly better. The behaviour of the algorithm is examined when constructing pruned classifiers. The ways to improve standard Machine Learning algorithms are suggested.
Highlights
Many decision making problems represent a category of classification tasks
A single classifier is constructed as a result of standard use of Machine Learning (ML) algorithms, methods of classifier ensembles construction became very popular lately
This study proposes an analysis of the algorithm for the combined use of genetic algorithms (GA) and heuristic search strategies [6] that enables using the advantages of GA along with such possibilities of heuristic search as decision tree construction and finding a set of rules that are able to explain the hidden regularities in the domain under consideration
Summary
Many decision making problems represent a category of classification tasks. The developers of these systems are usually concentrated on such parameters as computation cost and learning method accuracy. A single classifier is constructed as a result of standard use of Machine Learning (ML) algorithms, methods of classifier ensembles construction became very popular lately. These ensembles demonstrate better recognition quality for the objects that were not represented in the test set. 3. To study the behaviour of the algorithm when constructing pruned classifiers. Study the accuracy of classification depending on pruning extent of the classifier taught
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
