On-line learning by active sampling using orthogonal decision support vectors
Jong-Min Park · 2002
Active-sampling-at-the-boundary method is applied using orthogonal decision support vectors to facilitate pattern classification in identifying optimal decision boundary for a stochastic oracle. The result of the active sampling near the boundary using these vectors is shown in comparison with active learning using random selection in the multi-dimensional decision hyperplane. This shows the optimality of boundary active sampling using decision support vectors in the case of non-separable linear decision hyperplanes in multi-dimensional space.