Information-Theoretic Objective Functions for Lifelong Learning

Abstract

Conventional paradigms of machine learning assume all the training data are available when learning starts. However, in lifelong learning, the examples are observed sequentially as learning unfolds, and the learner should continually explore the world and reorganize and refine the internal model or knowledge of the world. This leads to a fundamental challenge: How to balance long-term and short-term goals and how to trade-off between information gain and model complexity? These questions boil down to "what objective functions can best guide a lifelong learning agent?" Here we develop a sequential Bayesian framework for lifelong learning, build a taxonomy of lifelong-learning paradigms, and examine information-theoretic objective functions for each paradigm, with an emphasis on active learning. The objective functions can provide theoretical criteria for designing algorithms and determining effective strategies for selective sampling, representation discovery, knowledge transfer, and continual update over a lifetime of experience.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2012
Accession Number
ADA570257

Entities

People

  • Byoung-tak Zhang

Organizations

  • Seoul National University

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Bayesian Inference
  • Bayesian Networks
  • Cognitive Science
  • Computer Science
  • Information Processing
  • Machine Learning
  • Models
  • Neural Networks
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Reinforcement Learning
  • Simultaneous Localization And Mapping

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks