Online learning and active learning: A comparative study of passive-aggressive algorithm with support vector machine (SVM)

Abstract

Passive aggressive online learning is an extension of Support Vector Machine (SVM) to the context of online learning for binary classification. In this paper we consider the application of the algorithm on anomaly labeling for IJCNN 2001 Neural Network Competition dataset from LibSVMdataset repository1 from Ford Research Laboratory. We also work on an improved version of the online learning algorithm called Active learning and we compare both algorithms to that of SVM (from LibSVM library). We propose different experimental setups for comparing the algorithms.