In the field of Artificial Intelligence (AI), Machine Learning (ML) techniques and algorithms have been employed in a wide variety of domains and have demonstrated incredible capabilities as well as continued applicability to an ever-expanding number of areas and applications. Image and speech recognition, medical diagnosis, classification and prediction, information extraction (i.e., deep learning), commercial market and customer analysis, robotics, and self-driving vehicles are a few of the many areas where ML has either made possible or had a significant impact. Yet for all this progress, the field of AI has not yet approached what many consider the holy grail of AI: machines with human-like intelligence. Causal analysis is essential for realizing the vision of human-like reasoning: it brings the ability to determine cause-effect relationships and provides a basis for reasoning about interventions (i.e., doing), as well as what might have happened had events occurred differently (i.e., imagining/retrospection) which are fundamental characteristics of human reasoning. Causal analysis has seen widespread use and success in epidemiology, social science, and other fields for decades. Even so, its use in engineering, computer science, and AI has been limited and its potential is just beginning to be widely recognized and applied.
FULL ARTICLE HERE