Fundamental principals of Computational Learning Theory

摘要

This paper presents some major key points of Computational Learning Theory, which describes fundamental building blocks of a mathematical formal representation of a cognitive process. The excerpt of the theory outlines and pinpoints the importance of having a distribution-free model that represents a learning process implementation for text classification purposes, widely adapted by Machine Learning. The authors emphasize on the importance of Probably Approximately Correct Learning paradigm and Efficient Learning solutions within acceptable running time of algorithms with high confidence and accuracy results. The examples that will be looked at will provide additional understanding of the theory and its application in the real world.