Optimal Learning for Efficient Experimentation in Nanotechnology and Biochemistry

Abstract

The objective of this research is to investigage the problem of optimizing the sequential management of experiments in materials science, with special emphasis on nano and bio technologies. The work will focus on a class of sequential policies based on a Bayesian belief model which takes full advantage of the extensive level of domain knowledge shared by scientists in this field. The knowledge gradient policy is particularly well suited to maximize the rate of learning while exploiting domain knowledge through an interactive learning experience.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 23, 2016
Source ID
FA95501610046

Entities

People

  • Warren B. Powell

Organizations

  • Air Force Office of Scientific Research
  • Trustees of Princeton University
  • United States Air Force

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Research Science/Academic Research
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Biotechnology