We present an algorithm for building a discriminative models by observing only a single or a few data points at a time. The algorithm is and extension of the multivariate online Kernel Density Estimator, and uses a new measure of discrimination loss to determine how much a classifier can be compressed without modyfing its performance.

This research deals with building online multivariate probability density functions from data streams. The strictest scnario is considered in which the data point is observed once and directly integrated into the model. A Kernel density estimator is proposed to deal with this.

This research deals with the problem of incrementally building a generative model from data using a positive as well as negative examples. We propose an incremental update rule for building one dimensional Gaussian mixture models based on Kernel Density Estimation that support learning from negative examples.