ScienceandTechnologyIntelligencetestingWhoareyou

1、聽力課堂,開放式英語學(xué)習(xí)平臺(tái)！www.TingCScience and Technology Intelligence testing Who are you calling bird-brained?科技 智力測(cè)試 叫誰是笨蛋呢?An attempt is being made to devise a universal intelligence test人類正嘗試設(shè)計(jì)一種通用的智力測(cè)驗(yàn)WHAT is the IQ of a chimpanzee? Or a worm? Or a game-show-winning computer program? Or even an alien fro

2、m the planet Zaarg who can learn any human language in a day, can beat grandmasters ten at a time and can instantly factor the products of large prime numbers?黑猩猩、蠕蟲或用于智力競(jìng)賽的計(jì)算機(jī)程序，甚至是來自Zaarg星球的外星人(外星人能在一天內(nèi)學(xué)會(huì)任何一門人類語言，每次都能贏棋類大師10分，能立即分解出大質(zhì)數(shù)的因子)，它們的智商是多少呢?At the moment it is impossible to say.當(dāng)問到這類問題，沒有

3、人能回答出來。IQ tests depend on language, and even Watson, a computer program that beat two human contestants in a special edition of Jeopardy! (an American quiz show) on February 16th, does not have a perfect command of English.IQ測(cè)試依賴于語言，而且就算是Watson系統(tǒng)對(duì)英語也不是了如指掌(2月16日，Watson系統(tǒng)在美國智力競(jìng)賽Jeopardy!的特別節(jié)目中擊敗了兩名人類

4、對(duì)手)。In any case there is, at the moment, no meaningful scale on which non-human intelligence can be compared with the human sort.但不管怎么樣，現(xiàn)在還沒有一個(gè)有意義的標(biāo)尺能用于任何非人類和人類智商的比較。The most famous test for artificial intelligence is that devised by Alan Turing, a British computing pioneer.最著名的人工智力測(cè)試是由英國計(jì)算科學(xué)先驅(qū)阿蘭圖靈(

5、Alan Turing)設(shè)計(jì)的。To pass the Turing test, and thus be considered intelligent, a program must fool a human being into believing that it is another human being.為了通過圖靈測(cè)試，機(jī)器中的程序必須使對(duì)方(人類)誤以為它也是一個(gè)人類，且如果機(jī)器通過了測(cè)試，該機(jī)器就被認(rèn)為是人工智能。But the Turing test still requires the program to share a language with the tester a

6、nd, because it is all or nothing, cannot be used to rank different forms of artificial intelligence against one another.但圖靈測(cè)試仍要求程序和測(cè)試者使用相同的語言。并且由于測(cè)試的結(jié)果是是或者否，因此不能用于不同形式人工智能間的評(píng)級(jí)。Jose Hernandez-Orallo of the Polytechnic University of Valencia, in Spain, and David Dowe of Monash University, in Australia

7、, think they can do better than this. They believe not only that a universal scale of intelligence can be devised, but also that it can be assessed without reference to language.If they are right, an insult like bird-brained will, in the future, be finely calibrated.來自西班牙瓦倫西亞理工大學(xué)的Jose Hernandez-Oral

8、lo和澳大利亞莫納什大學(xué)的David Dowe認(rèn)為他們能設(shè)計(jì)出比圖靈更完善的測(cè)試。他們相信不僅能設(shè)計(jì)出可通用的智商標(biāo)尺，而且測(cè)試可以與語言無關(guān)。如果真能如他們所說，那么將來就可以精確計(jì)算出愚蠢的程度了。Dr Hernandez-Orallo and Dr Dowe, both computer scientists, propose to make their measurement by borrowing a concept called Kolmogorov complexity from information theory, a branch of computer science.

9、Hernandez-Orallo博士和Dr Dowe博士都是計(jì)算機(jī)科學(xué)家，他們提出：借用信息論(計(jì)算機(jī)科學(xué)的一個(gè)分支)中的Kolmogorov復(fù)雜度概念來實(shí)現(xiàn)測(cè)量。The Kolmogorov complexity of a computers output is the shortest possible program (measured in the binary digits that lie at the bottom of all computer code) that could produce that output.計(jì)算機(jī)輸出的Kolmogorov復(fù)雜度是指能產(chǎn)生該輸出的可能

10、最短程序(基于計(jì)算機(jī)代碼的二進(jìn)制位數(shù))。On this measure, an entitys intelligence would be measured by the Kolmogorov complexity of the most complex tests it can solvea clear, numerical value.在這種設(shè)計(jì)下，可以通過最復(fù)雜測(cè)試的Kolmogorov復(fù)雜度來測(cè)量一個(gè)實(shí)體的智商。In practice, calculating the true Kolmogorov complexity of a system is almost impossible

11、.實(shí)際上，要正確計(jì)算出系統(tǒng)的Kolmogorov復(fù)雜度幾乎是不可能的。But an approximation can be made. And that, the researchers reckon, will be good enough.但可以計(jì)算出它的近似值。而對(duì)研究人員的估算工作而言，近似值也就足夠了。The actual tests would employ the well-honed methods of operant conditioning, developed initially on pigeons, in which the test subject has fi

12、rst to work out what is going on by trial and error.實(shí)際的測(cè)試會(huì)采用精確的操作性條件反射方法，測(cè)試對(duì)象首先要清楚實(shí)驗(yàn)的過程和錯(cuò)誤。As in operant conditioning, correct responses would be ewardedby money, perhaps, for a human being; by bananas for a chimpanzee or by the numerical value itself for an appropriately programmed computer.在操作性條件反

13、射中，正確的反射響應(yīng)將得到獎(jiǎng)勵(lì)對(duì)人而言可能是金錢，對(duì)黑猩猩而言是香蕉，對(duì)可編程計(jì)算機(jī)而言則可能是數(shù)值本身。If the test were noughts and crosses, the test-taker (if it had never seen the game before) would first have to work out that the game is won by getting three in a row on a 3-by-3 grid, before actually going on to play.如果測(cè)驗(yàn)是畫圈叉游戲，則在進(jìn)行游戲之前測(cè)試參與者(假定他

14、們從沒聽說過圈叉游戲)首要要弄懂在3X3的網(wǎng)格中，3個(gè)格連成一行就贏得游戲了。A chimpanzee might not manage a test of this level of complexity, but could, maybe, work out the idea of three-in-a-row when only a single row was involved.黑猩猩可能沒辦法理解這種復(fù)雜度等級(jí)的測(cè)驗(yàn)，但當(dāng)只有一行時(shí)，它們也許就可以明白3格-1行的概念了。Chess, though, would surely be beyond it (and probably be

15、yond most people, too, if they did not already know the rules).而象棋的難易度遠(yuǎn)超過黑猩猩的理解程度(可能也超過大多數(shù)人的理解，如果他們并不知道象棋規(guī)則的話)。Games like draughts and dominoes would lie somewhere in between.西洋跳棋和多米諾骨牌這類游戲的難易程度則介于圈叉和象棋之間。In fact Dr Hernandez-Orallo and Dr Dowe do not plan to use existing games. Instead they are employing a computer to enerate novel games and patterns.實(shí)際上，Hernandez-Orallo博士和Dowe博士計(jì)劃采用計(jì)算機(jī)產(chǎn)生的新游戲和新花樣來代替已有的游戲。Their approach eliminates human bias.他們的方法消除了人類的偏見，It also allows them to generate tests with any level of complexity they likeeven ones t