Unifying Robustness to Uncertain Perturbations in Statistical Learning and Inference

Abstract

Machine learning (ML), deep learning (DL), and artificial intelligence (AI) tools adapted to the tactical theater will play an instrumental role in next generation C4ISR systems of the land forces. Attuned to the Army s network-centric vision, this proposal is centered around principled graph-guided ML and DL with scalability, robustness, and quantifiable performance in unknown, dynamic, congested, and contested operational environments. By effectively identifying perturbed nodes and links compromised by high-tech adversaries, as well as fusing trustworthy information from the `Internet of Battlefield ThingsÕ (including humans in the loop) with quantifiable reliability even in blind settings, will specifically enable robust mission-driven learning capabilities to autonomously recognize, model, and anticipate dynamic changes in network information processes.

Document Details

Document Type
DoD Grant Award
Publication Date
Jun 25, 2021
Source ID
W911NF2110297

Entities

People

  • Georgios B. Giannakis

Organizations

  • Army Contracting Command
  • United States Army
  • University of Minnesota

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.

Technology Areas

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