Home | Publications | CS Home

The Role of Forgetting in Learning


Shaul Markovitch and Paul Scott. The Role of Forgetting in Learning. In Proceedings of The Fifth International Conference on Machine Learning, 459-465 Ann Arbor, MI, 1988.Morgan Kaufmann


Abstract

This paper is a discussion of the relationship between learning and forgetting. An analysis of the economics of learning is carried out and it is argued that knowledge can sometimes have a negative value. A series of experiments involving a program which learns to traverse state spaces is described. It is shown that most of the knowledge acquired is of negative value even though it is correct and was acquired solving similar problems. It is shown that the value of the knowledge depends on what else is known and that random forgetting can sometimes lead to substantial improvements in performance. It is concluded that research into knowledge acquisition should take seriously the possibility that knowledge may sometimes be harmful. The view is taken that learning and forgetting are complementary processes which construct and maintain useful representations of experience.


Keywords: Forgetting, Utility Problem, Macro Learning
Secondary Keywords:
Online version:
Bibtex entry:
 @inproceedings{Markovitch:1988:RFL,
  Author = {Shaul Markovitch and Paul Scott},
  Title = {The Role of Forgetting in Learning},
  Year = {1988},
  Booktitle = {Proceedings of The Fifth International Conference on Machine Learning},
  Pages = {459--465},
  Address = {Ann Arbor, MI},
  Url = {http://www.cs.technion.ac.il/~shaulm/papers/pdf/Markovitch-Scott-icml1988.pdf},
  Keywords = {Forgetting, Utility Problem, Macro Learning},
  Secondary-keywords = {Redundant Knowledge, Explanation-Based Learning, Information Filtering, Deductive Learning},
  Abstract = {
    This paper is a discussion of the relationship between learning
    and forgetting. An analysis of the economics of learning is
    carried out and it is argued that knowledge can sometimes have a
    negative value. A series of experiments involving a program which
    learns to traverse state spaces is described. It is shown that
    most of the knowledge acquired is of negative value even though it
    is correct and was acquired solving similar problems. It is shown
    that the value of the knowledge depends on what else is known and
    that random forgetting can sometimes lead to substantial
    improvements in performance. It is concluded that research into
    knowledge acquisition should take seriously the possibility that
    knowledge may sometimes be harmful. The view is taken that
    learning and forgetting are complementary processes which
    construct and maintain useful representations of experience.
  }

  }