Open AccessAutomated Classification using SVM and Back Propogation Learning Technique
Author(s) -
Pravik Solanki,
D.R. Prajapati
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.c8350.049620
Subject(s) - support vector machine , computer science , artificial intelligence , machine learning , generalization , artificial neural network , kernel (algebra) , supervised learning , pattern recognition (psychology) , mathematics , mathematical analysis , combinatorics
In this paper the comparative study of two supervised machine learning techniques for classification problems has been done. Due to the real-time processing ability of neural network, it is having numerous applications in many fields. SVM is also very popular supervised learning algorithm because of its good generalization power. This paper presents the thorough study of the presented classification algorithm and their comparative study of accuracy and speed which would help other researchers to develop novel algorithms for applications. The comparative study showed that the performance of SVM is better when dealing with multidimensions and continuous features. The selection and settings of the kernel function are essential for SVM optimality.