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

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks