Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution
This work addresses the foundational problem of enabling strong AI by shifting from model-free to model-based approaches, which is crucial for researchers and practitioners in AI and machine learning.
The paper argues that current statistical machine learning systems are fundamentally limited because they cannot reason about interventions and retrospection, which are essential for achieving human-level intelligence. It demonstrates this by presenting seven tasks that are beyond the reach of current systems but have been accomplished using causal modeling tools.
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.