This is the webpage of the project "Anytime Universal Intelligence" (anYnt).(alpha november yankee november tango)

  • Funding Entity: MEC (Ministerio de Educación y Ciencia), AYUDAS PARA LA REALIZACIÓN ACCIONES COMPLEMENTARIAS DENTRO DEL PROGRAMA NACIONAL DE PROYECTOS DE INVESTIGACIÓN FUNDAMENTAL, PLAN NACIONAL DE I+D+i 2008-2011

  • Type of Project: EXPLORA

  • Acceptance rate: 14 from 98 (14.2%)

  • Reference: TIN2009-06078-E/TIN

  • Period: September 2009 - December 2011

The project is already finished and this webpage not properly maintained, but we still keep an account of related publications and news here


SUMMARY OF THE PROJECT:

Following ideas from the first intelligence definitions and tests based on Algorithmic Information Theory [Dowe and Hajek 1997] [Hernandez-Orallo 2000a] [Legg and Hutter 2007], we face the challenge of constructing the first universal, formal, but at the same time practical, intelligence test. The key issue is the notion of "anytime" test, which will allow a quick convergence of the test to the subject's level of intelligence and a progressively better assessment the more time we provide. The ultimate goal is that science will be able some day to measure intelligence of higher animals (e.g. apes), humans and machines in a universal and practical way.


WORKING TEAM:


FULL DESCRIPTION OF THE PROJECT:

A full description of the project (as of its original proposal in March 2009) can be found here.


REPORTS AND PAPERS INSIDE THE PROJECT:

For a more recent list of publications (of this and other topics), you can also click : here or here.


RELATED PROJECTS, PRESENTATIONS AND PAPERS:


OUR TESTS:

In this section we will include the tests we developed during the project.


SOFTWARE:


Other tests, contests and systems:


In the Media (and humour):

Please don't take this section too seriously. Not all journalists know what a quoted text means. We haven't said everything that they say we say.

In English:

In Spanish:

Other languages:

Interviews and write-ups:

After all this empirical evidence with the media, we've developed a new concept called "anytime media" ;-)

Namely,

We have also proved the "anytime media theorem": Given an interview with the media, the output is completely independent from the input.

And finally, you're now ready for this ;-)


A smart machine will first consider which is more worth its while: to perform the given task or, instead, to figure some way out of it. Whichever is easier. And why indeed should it behave otherwise, being truly intelligent? For true intelligence demands choice, internal freedom. And therefore we have the malingerants, fudgerators, and drudge-dodgers, not to mention the special phenomenon of simulimbecility or mimicretinism. A mimicretin is a computer that plays stupid in order, once and for all, to be left in peace. And I found out what dissimulators are: they simply pretend that they're /not/ pretending to be defective. Or perhaps it's the other way around. The whole thing is very complicated. A probot is a robot on probation, while a servo is one still serving time. A robotch may or may not be a sabot. One vial, and my head is splitting with information and nomenclature. A confuter, for instance, is not a confounding machine — that's a confutator — but a machine which quotes Confucius. A grammus is an antiquated frammus, a gidget — a cross between a gadget and a widget, usually flighty. A bananalog is an analog banana plug. Contraputers are loners, individualists, unable to work with others; the friction these types used to produce on the grid team led to high revoltage, electrical discharges, even fires. Some get completely out of hand — the dynamoks, the locomoters, the cyberserkers. Stanislaw Lem
Please feel free to contact us at jorallo@dsic.upv.es.