Machine-Learning Theory and Its Policy Implications

Digital Policy Hub Working Paper

April 25, 2024

The goal of this paper is to present an intuitive summary of computational learning theory, and its application for analyzing the most popular learning algorithms in machine learning, neural networks. This paper assumes no mathematical background or knowledge of machine learning from the reader. Throughout the paper, the important sections are presented using a pyramid approach (that is, in three levels). After introducing each major idea/topic, its policy implications and connection to Canada’s law are discussed. Finally, a summary of Canada’s relevant artificial intelligence law, with a case example, is given.

About the Author

Naod Abraham is a third-year mathematical physics student at the University of Waterloo with an interest in computer science. His research with the Digital Policy Hub will investigate the applications of machine learning for practically important problems.