Skip to main content Accessibility help
×
Hostname: page-component-5c6d5d7d68-wpx84 Total loading time: 0 Render date: 2024-09-01T07:19:15.694Z Has data issue: false hasContentIssue false

9 - Copycat: Analogical AI

Hofstadter's Romantic Dream

Published online by Cambridge University Press:  05 June 2012

H. R. Ekbia
Affiliation:
Indiana University
Get access

Summary

I am a romantic who tends to see the power and depth of human creativity as virtually limitless…. I hope thereby to convey the attitude that in AI …, one should not expect full success overnight – nor should anyone want it.

– Douglas Hofstadter: Le Ton beau de Marot

Copycat is a computer model of analogy-making in the domain of letter-string puzzles. Given an analogy problem such as “abcabd; iijjkk ⇒?”, for example, it comes up with a set of various answers such as iijjll, iijjdd, iijjkl, iijjkd, iijjkk, iikjkk, iidjkk, or even abd or aabbdd.

Puzzles such as these are common in aptitude tests because apparently they provide useful measures of people's intelligence and creativity. Copycat, by the same token, is believed to have some degree of creativity, albeit a minute one. This model, its successor Metacat, and its siblings Letter Spirit, Tabletop, Phaeaco, and others owe their original conception to Douglas Hofstadter and his Fluid Analogies Research Group. Hofstadter believes that analogies are at the core of human cognition and creativity, and that computer models of analogy-making can provide useful insights into the mechanisms underlying the marvels of human intelligence, from art to science and from language to music. In this chapter, we study a few models of creativity and analogy-making, in particular Copycat, which is based on Hofstadter's views.

Type
Chapter
Information
Artificial Dreams
The Quest for Non-Biological Intelligence
, pp. 286 - 308
Publisher: Cambridge University Press
Print publication year: 2008

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Save book to Kindle

To save this book to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

  • Copycat: Analogical AI
  • H. R. Ekbia, Indiana University
  • Book: Artificial Dreams
  • Online publication: 05 June 2012
  • Chapter DOI: https://doi.org/10.1017/CBO9780511802126.011
Available formats
×

Save book to Dropbox

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Dropbox.

  • Copycat: Analogical AI
  • H. R. Ekbia, Indiana University
  • Book: Artificial Dreams
  • Online publication: 05 June 2012
  • Chapter DOI: https://doi.org/10.1017/CBO9780511802126.011
Available formats
×

Save book to Google Drive

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Google Drive.

  • Copycat: Analogical AI
  • H. R. Ekbia, Indiana University
  • Book: Artificial Dreams
  • Online publication: 05 June 2012
  • Chapter DOI: https://doi.org/10.1017/CBO9780511802126.011
Available formats
×