Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution

TL;DR

This paper argues that current machine learning systems are limited by their statistical approach and cannot achieve human-level intelligence without causal models that enable reasoning about interventions and reality.

Contribution

It highlights the necessity of causal inference models for advancing machine learning towards human-like reasoning and presents seven tasks that demonstrate their importance.

Findings

Current ML systems lack causal reasoning capabilities.

Seven key tasks demonstrate the success of causal models.

Causal inference is essential for strong AI development.

Abstract

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.