Bayesian Program Learning and Concept Induction

Abstract

Tenenbaum proposes to investigate and formalize an approach to learning and concept formation that will provide measureable results indicating significant reduction in costs for a system to learn and formulate new concepts. His work will focus on Bayesian inference to perform learning and concept induction. Many machine learning approaches require large populations of learning examples as training sets used to train learning algorithms. Tenenbaum asks the question, why do supervised learning algorithms require such large numbers of learning examples when in contrast, children often quickly learn a new concept with just one learning example.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 23, 2016
Source ID
FA95501610012

Entities

People

  • Joshua B. Tenenbaum

Organizations

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

Tags

Fields of Study

  • Computer science

Readers

  • Joint Military Operations and Doctrine.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks