Bridging Data-Intensive and Knowledge-Intensive Methods for Scientific and Mathematical Discovery

Abstract

The PIs, Dr. Carla Gomes and Dr. Bart Selman, proposes research addressing the challenges that mathematical and scientific discovery domains pose to existing machine learning algorithms. Specifically, they will focus on highly structured systems and integrate rich prior domain knowledge into their (learned) models of these systems; this is a key part of the learning. These models ought to adhere to mathematical and physical constraints and reveal true causal principles of the systems being studied, as well as be interpretable. Ultimately, the learned models should reveal new scientific insights and guide practical decision and experimental validation.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 06, 2024
Source ID
FA95502310322

Entities

People

  • Bart Selman

Organizations

  • Air Force Office of Scientific Research
  • Cornell University
  • United States Air Force

Tags

Readers

  • Artificial Intelligence
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks