Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

Peacewise comments on "Inductive Bias" - Less Wrong

21 Post author: Eliezer_Yudkowsky 08 April 2007 07:52PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (24)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Peacewise 13 November 2011 01:26:19AM -1 points [-]

Seems to me that the educational psychology term "overextension" has some relevance to the white swan scenario mentioned above. "overextension - inappropriate use of a word for a class of things rather than for one particular thing." Definition provided by Krause, K., Bochner, S., Duchesne, S., & McMaugh, A. (2010). Educational psychology for learning & teaching (3rd ed.). South Melbourne: Cengage Learning Australia. Strictly going from seeing one white swan to labelling therefore, all swans are white is inappropriate, hence why I think overextension is relevant, it mainly occurs within very young children. I imagine that if AI are overextending then they may be displaying characteristics of 2/3 year old children, this may or may not be useful. Some parts of the below discussion mention prior's in the same way that a psychologist would use the term heuristic. "heuristic - a thinking strategy that enables quick, efficient judgements." Social Psychology 10th Edition by David Myers. It may well be useful to go from seeing one white swan to all swans are white, in that it may be a thinking strategy that enables quick efficient recognition of a swan. Perhaps this may be a first look scenario, a person (or ai) glimpses the whiteness and rough shape of a swan and provides a quick working label of "swan", then if necessary firms up that label with a refresh to gather more specific information, or simply holds the swan label if it's not necessarily needed.