Model-enhanced Machine Learning and Decision

Abstract

This general aim of this proposal is to extend the capabilities of machine learning systems through the use of causal and counterfactual information. The proposal is motivated by the observation that current machine learning systems operate, almost exclusively, in a purely statistical mode, which puts severe theoretical limits on their performance. We here propose to leverage counterfactual logic to enhance two classes of applications. (1) Learning individual behavior from population data, and (2) Automating attention and curiosity.

Document Details

Document Type
DoD Grant Award
Publication Date
Jun 09, 2021
Source ID
N000142112351

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