Practical Machine Learning, Causal Learning and Bayesian Belief Networks for System Simulation, Test and Predictive Maintenance

Abstract

The following concepts represent current SEI research and customer support of programs within the USAF and Navy. Although machine learning and deep learning are not novel in their application, our complement of causal learning to segregate true causal influence from spurious correlation enable us to go one step further in providing more actionable models.The avionics system depicted in these slides could be any system. The methodology would be unchanged across domains. We first discuss potential improvement in system simulation and test via machine and causal learning followed by improvement in system diagnosis via BBNs informed from machine and causal learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 14, 2018
Accession Number
AD1087825

Entities

People

  • Robert W. Stoddard

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Contracts
  • Department Of Defense
  • Engineering
  • Guarantees
  • Learning
  • Machine Learning
  • Materials
  • Software Development
  • Universities

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Modeling and Simulation

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks