Effective Bayesian Transfer Learning

Abstract

The general theme of the project is transfer learning, i.e., the process whereby the learning process in task Y is improved by prior learning experience in task X. The project addresses transfer learning in three application areas: strategy games, robotic object manipulation, and visual object recognition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2010
Accession Number
ADA516458

Entities

People

  • Leslie P. Kaelbling
  • Tomas Lozano-Pérez

Organizations

  • University of California, Berkeley

Tags

Communities of Interest

  • Autonomy
  • Biomedical
  • C4I
  • Weapons Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Bayesian Networks
  • Computational Science
  • Computer Languages
  • Computer Vision
  • Information Processing
  • Information Science
  • Linear Programming
  • Machine Learning
  • Network Science
  • Neural Networks
  • Operations Research
  • Probabilistic Models
  • Probability
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Defense Technology Research and Development.
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • Autonomy