Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Computational Complexity of Learning

  • Sanjay Jain
  • Frank Stephan
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_151


Measures of the complexity of learning have been developed for a number of purposes including  Inductive Inference,  PAC Learning, and  Query-Based Learning. The complexity is usually measured by the largest possible usage of ressources that can occur during the learning of a member of a class. Depending on the context, one measures the complexity of learning either by a single number/ordinal for the whole class or by a function in a parameter ndescribing the complexity of the target to be learnt. The actual measure can be the number of mind changes, the number of queries submitted to a teacher, the number of wrong conjectures issued, the number of errors made or the number of examples processed until learning succeeds. In addition to this, one can equip the learner with an oracle and determine the complexity of the oracle needed to perform the learning process. Alternatively, in complexity theory, instead of asking for an NP-complete oracle to learn a certain class, the...

This is a preview of subscription content, log in to check access.

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Sanjay Jain
  • Frank Stephan

There are no affiliations available