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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2012
- Accession Number
- ADA570257
Entities
People
- Byoung-tak Zhang
Organizations
- Seoul National University