What is Gained from Past Learning

Abstract

We consider ways of enabling systems to apply previously learned information to novel situations so as to minimize the need for retraining. We show that theoretical limitations exist on the amount of information that can be transported from previous learning, and that robustness to changing environments depends on a delicate balance between the relations to be learned and the causal structure of the underlying model. We demonstrate by examples how this robustness can be quantified.

Document Details

Document Type
Pub Defense Publication
Publication Date
Mar 01, 2018
Source ID
10.1515/jci-2018-0005

Entities

People

  • Judea Pearl

Organizations

  • Defense Advanced Research Projects Agency
  • National Science Foundation
  • Office of Naval Research
  • University of California

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design