Eager learning

from Wikipedia, the free encyclopedia

Eager learning ( Engl. "Eager learning") is a class of machine learning methods . In contrast to lazy learning , the modeling takes place offline once on the basis of the training data and not online at the time of the request. The advantage is that while this increases the time required for training through the modeling, the query time is significantly reduced.

In contrast to lazy learning , however, the model can only be created globally over the entire training data set, not locally around the working point , since this is not known at the time of training / learning.

literature

  • David W. Aha: Lazy learning . Kluwer Academic Publishers, Norwell 1997, ISBN 0-7923-4584-3 .
  • Peter Auer: On Learning From Multi-Instance Examples . Empirical Evaluation of a Theoretical Approach. In: ICML '97: Proceedings of the Fourteenth International Conference on Machine Learning . Morgan Kaufmann Publishers, San Francisco 1997, ISBN 1-55860-486-3 , pp. 21-29 .

Individual evidence

  1. ↑ David W. Aha: Lazy learning . Kluwer Academic Publishers, Norwell 1997, ISBN 0-7923-4584-3 .