Title :
Convergence and application of online active sampling using orthogonal pillar vectors
Author_Institution :
Dept. of Electr. & Comput. Eng., San Diego State Univ., CA, USA
Abstract :
The analysis of convergence and its application is shown for the Active Sampling-at-the-Boundary method applied to multidimensional space using orthogonal pillar vectors. Active learning method facilitates identifying an optimal decision boundary for pattern classification in machine learning. The result of this method is compared with the standard active learning method that uses random sampling on the decision boundary hyperplane. The comparison is done through simulation and application to the real-world data from the UCI benchmark data set. The boundary is modeled as a nonseparable linear decision hyperplane in multidimensional space with a stochastic oracle.
Keywords :
convergence; learning (artificial intelligence); pattern classification; sampling methods; stochastic processes; support vector machines; UCI benchmark data set; convergence; decision boundary hyperplane; linear optimal decision hyperplane; machine learning; multidimensional space; online active sampling-at-the-boundary method; orthogonal pillar vectors; pattern classification; standard active learning method; stochastic oracle; Application software; Convergence; Learning systems; Machine learning; Multidimensional systems; Pattern classification; Sampling methods; Stochastic processes; Training data; Vectors; Index Terms- Active learning; machine learning; pattern classification.; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Information Storage and Retrieval; Models, Statistical; Online Systems; Pattern Recognition, Automated; Reproducibility of Results; Sample Size; Sensitivity and Specificity; Signal Processing, Computer-Assisted;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2004.61
