Dynamic Dimensionality Selection for Bayesian Classifier Ensembles.

摘要

This project seeked to develop new learning algorithms specifically tailored to be efficient and effective in learning from big data. It exploited the capacity of generative learning to efficiently extract useful summary statistics and used discriminative learning to meld them into a highly accurate classifier. Two classes of learning algorithm were developed. The first uses discriminative learning to select a generative model (selective ANDE and selective KDB). Very effective feature selection was achieved with a single pass through the training data for each attribute that is finally selected. The second combines generatively and discriminatively learned parameters (WANBIA, WANBIA-C,WANJE). It uses discriminative learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very competitive to Logistic Regression but much more efficient in learning the model. WNANJE can model higher-order attribute interdependencies.