Predictive learning

Predictive learning is a technique of machine learning in which an agent tries to build a model of its environment by trying out different actions in various circumstances. It uses knowledge of the effects its actions appear to have, turning them into planning operators.[1][2] These allow the agent to act purposefully in its world. Predictive learning is one attempt to learn with a minimum of pre-existing mental structure. It may have been inspired by Piaget's account of how children construct knowledge of the world by interacting with it. Gary Drescher's book 'Made-up Minds'[3] was seminal for the area.

The idea that predictions and Unconscious inference are used by the brain to construct a model of the world, in which it can identify causes of percepts, is however even older and goes at least back to Hermann von Helmholtz.[4] Those ideas were later picked up in the field of Predictive coding.

Another related predictive learning theory is Jeff Hawkins' memory-prediction framework, which is laid out in his On Intelligence.[5]

See also

References
  1. "Erica Melis & Alan Bundy: Planning and Proof Planning" (PS-Adobe-2.0 (52,83 kiB)). 1996. Retrieved 2018-11-22.
  2. "J. Siekmann, M. Kohlhase and E. Melis: Ωmega – A Mathematical Assistant System". 1998. Retrieved 2021-04-05.
  3. Gary L. Drescher (1991). Make-up Minds: A Constructivist Approach to Artificial Intelligence. MIT Press. p. 240. ISBN 9780262041201.
  4. Hermann von Helmholtz (1867). Handbuch der physiologischen Optik.
  5. Jeff Hawkins & Sandra Blakeslee (2004). On Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines. USA: Times Books. p. 272. ISBN 0805074562.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.