Machine Learning

, Volume 15, Issue 2, pp 201-221

First online:

Improving Generalization with Active Learning

  • David CohnAffiliated withDepartment of Brain and Cognitive Sciences, Massachusetts Institute of Technology
  • , Les AtlasAffiliated withDeptartment of Electrical Engineering, University of Washington
  • , Richard LadnerAffiliated withDeptartment of Computer Science and Engineering, University of Washington


Active learning differs from “learning from examples” in that the learning algorithm assumes at least some control over what part of the input domain it receives information about. In some situations, active learning is provably more powerful than learning from examples alone, giving better generalization for a fixed number of training examples.

In this article, we consider the problem of learning a binary concept in the absence of noise. We describe a formalism for active concept learning called selective sampling and show how it may be approximately implemented by a neural network. In selective sampling, a learner receives distribution information from the environment and queries an oracle on parts of the domain it considers “useful.” We test our implementation, called an SG-network, on three domains and observe significant improvement in generalization.

queries active learning generalization version space neural networks