AI summary

This paper introduces lifelong learning approaches for object recognition that transfer knowledge across tasks to generalize more accurately from less data. The paper describes several memory-based and neural network algorithms. Experiments on a database of color camera images show that transferring knowledge from past learning tasks improves generalization accuracy.

Abstract

This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learning tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less training data. In this paper, several different approaches to lifelong learning are described, and applied in an object recognition domain. It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks.