Interpretable and Robust Artificial Intelligence

Abstract

We proposed safe AI systems. These AI systems are trusted because they are interpretable and resilient because they are robust. In particular, we pushed the state of the art in modern probabilistic modeling, including probabilistic models for causal inference. Probabilistic models provide a natural way for domain experts to express their assumptions and then to derive algorithms to compute under those assumptions. The results are interpretable because, for each model, we have a clear mathematical understanding of what is assumed, how the structure of the data interacts with the inferences, and the boundaries of what can and cannot be captured. With the methods we developed around causality, the resulting system will also be robust---robust to changes in the world and to interventions. To directly aid scientific discovery, we studied our methods on several problems in medical informatics, cancer therapy analysis, computational biology, and statistical astrophysics.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2023
Accession Number
AD1193162

Entities

People

  • David M. Blei

Organizations

  • Columbia University

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Engineered Resilient Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Bayesian Networks
  • Computational Biology
  • Computational Science
  • Computer Programming
  • Data Mining
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Monte Carlo Method
  • Network Science
  • Neural Networks
  • Probabilistic Models

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms
  • Space