Graduate Project

A framework for inconsistency induced perpetual learning system

The goal of this project is building a framework for Inconsistency Induced perpetual learning system and an UI to access the results, so that the users of the framework could understand all the options that are available in the framework. The proposed framework will accept the learning jobs with the given data set and generate learning models chosen by the user. The learned models tested against the test data set for any inconsistencies and if inconsistencies occurred, it triggers relearning. The implemented system built with distributed weka and Hadoop so that the framework supports very large dataset. The performance can be improved by attaching more nodes to the Hadoop cluster.