Causal reasoning and machine learning
In a recent paper titled "The Seven Pillars of Causal Reasoning with Reflections on Machine Learning", JUDEA PEARL, professor of computer science at UCLA and author of Causality popup: yes, writes:
“Current machine learning systems operate, almost exclusively, in a statistical or model-free mode, which entails severe theoretical limits on their power and performance. Such systems cannot reason about interventions and retrospection and, therefore, cannot serve as the basis for strong AI. To achieve human level intelligence, learning machines need the guidance of a model of reality, similar to the ones used in causal inference tasks. To demonstrate the essential role of such models, I will present a summary of seven tasks which are beyond reach of current machine learning systems and which have been accomplished using the tools of causal modeling."
The tasks include work on counterfactuals, and new approaches to handling incomplete data. Link popup: yes to the paper. A vivid expression of the issue: "Unlike the rules of geometry, mechanics, optics or probabilities, the rules of cause and effect have been denied the benefits of mathematical analysis. To appreciate the extent of this denial, readers would be stunned to know that only a few decades ago scientists were unable to write down a mathematical equation for the obvious fact that 'mud does not cause rain.' Even today, only the top echelon of the scientific community can write such an equation and formally distinguish 'mud causes rain' from 'rain causes mud.'”
Pearl also has a new book out, co-authored by DANA MCKENZIE, in which he argues for the importance of determining cause and effect in the machine learning context. From an interview in Quanta magazine about his work and the new book:
"As much as I look into what’s being done with deep learning, I see they’re all stuck there on the level of associations. Curve fitting. That sounds like sacrilege, to say that all the impressive achievements of deep learning amount to just fitting a curve to data. If we want machines to reason about interventions ('What if we ban cigarettes?') and introspection ('What if I had finished high school?'), we must invoke causal models. Associations are not enough—and this is a mathematical fact, not opinion.
We have to equip machines with a model of the environment. If a machine does not have a model of reality, you cannot expect the machine to behave intelligently in that reality. The first step, one that will take place in maybe 10 years, is that conceptual models of reality will be programmed by humans."