The Necessity of Machine Learning Theory in Mitigating AI Risk

Abstract

SUMMARY In the last years we have witnessed rapidly accelerating progress in Neural Network-based Artificial Intelligence. Yet our fundamental understanding of these methods has lagged far behind. Never before had a technology been developed so quickly and deployed so widely with so little understanding of its basic principles. In this document we argue that deep learning systems with their human-like complexity cannot be controlled and guided in socially acceptable ways or countered in adversarial situations, without an underlying theory. Theory in this context refers to identifying precise measurable quantities and mathematically describing their patterns, the way it is done in physics and engineering, rather than necessarily proving rigorous theorems.Given the societal impact of rapidly proliferating AI, developing such a theory and applying its analyses to real systems is a compelling and urgent need.