Enhancing Machine Learning with Causal and Counterfactual Information
Abstract
This proposal aims to extend the capabilities of machine learning systems through the use of causal andcounterfactual information. The proposal is motivated by the observation that current machine learning systemsoperate, almost exclusively, in a purely statistical mode, which puts severe theoretical limits on their performance. We propose to explore the feasibility of leveraging counterfactual reasoning in machine learning tasks, and to identify areas where such reasoning could lead to major breakthroughs in machine learning applications.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 04, 2017
- Source ID
- N000141712091
Entities
People
- Judea Pearl
Organizations
- Office of Naval Research
- United States Navy
- University of California, Los Angeles