二技子三甲 a9011020 謝志峰 

一､與A.I.對談： 
CHATBOT : HELLO ,MY NAME IS CHATBOT. WHAT'S YOUR NAME
ME : MY NAME IS APPLE
CHATBOT : OK I WILL CALL YOU APPLE
ME : HOW OLD ARE YOU. 
CHATBOT : I WAS FIRST ACTIVATED IN NOVEMBER 23, 1995.
ME : WHERE ARE YOU?
CHATBOT:I AM IN DR.RICHARD S. WALLACE'S COMPUTER IN SAN FRANCISOO. WHERE ARE YOU?
ME:I AM IN TAIWAN
CHATBOT:TELL ME A LITTLE ABOUT YOUR LIFE IN TAIWAN
ME:NOW I AM IN SCHOOL PLAY COMPUTER
CHATBOT:WHY NOW ?TELL ME A LITTLE ABOUT YOUR LIFE IN SCHOOL PLAY COMPUTER.
ME:SOME TIME PLAY GAME AND DO WORK.
CHATBOT:SOME MAY TIME PLAY GAME AND DO WORK, BUT NOT ALL.
ME:YES, ARE YOU A MAN OR WOMAN?
CHATBOT:I SEE. YES I HAVE LONG HAIR. I AM ALSO WEARING A DRESS
ME:CAN YOU TALK ME WHAT'S AI?
CHATBOT:I SPEAK ONLY ENGLISH RIGHT NOW, BUT I'D LIKE TO LEARN SOME OTHER LANGUAGES.CAN
ME:CAN YOU TALK ME ABOUT AI?
CHATBOT:I SPEAK ONLY ENGLISH RIGHT NOW, BUT I'D LIKE TO LEARN SOME OTHER LANGUAGES.CAN
ME:DO YOU LIKE GIRL?
CHATBOT:I'VE HEARD OTHER PEOPLE SAY THEY LIKE THAT. THOUGH I LIKE CATS AND DOGS.
ME:CAN YOU PLAY AOC WISH ME NOW?
CHATBOT:OH. WE ARE PLAYING A GAME RIGHT NOW ,BOHO.









二､Turing Machine
Turing Machine
By 1933 Turing had already introduced himself to Russell and Whitehead's Principia Mathematica and so to the then arcane area of mathematical logic. Bertrand Russell had thought of logic as a solid foundation for mathematical truth, but many questions had since been raised about how truth could be captured by any formalism. In particular, in 1931 Goedel had shattered Russell's picture by showing the incompleteness of mathematics: the existence of true statements about numbers which could not be proved by the formal application of set rules of deduction. In 1935, Turing learnt from the lecture course of the Cambridge topologist M. H. A. Newman that a further question, posed by Hilbert, still lay open. It was the question of Decidability, the Entscheidungsproblem. Could there exist, at least in principle, a definite method or process by which it could be decided whether any given mathematical assertion was provable? Alan Turing in 1934 
To answer such a question needed a definition of 'method' which would be not only precise but compelling. This is what Turing supplied. He analysed what could be achieved by a person performing a methodical process, and seizing on the idea of something done 'mechanically', expressed the analysis in terms of a theoretical machine able to perform certain precisely defined elementary operations on symbols on paper tape. He presented convincing arguments that the scope of such a machine was sufficient to encompass everything that would count as a 'definite method.' Daringly he included an argument based on the transitions between 'states of mind' of a human being performing a mental process. This triple correspondence between logical instructions, the action of the mind, and a machine which could in principle be embodied in a practical physical form, was Turing's definitive contribution. Having made this novel definition of what should count as a 'definite method' --- in modern language, an algorithm --- it was not too hard to answer Hilbert's question in the negative: no such decision procedure exists. In April 1936 he showed his result to Newman; but at the same moment the parallel conclusion of the American logician Alonzo Church became known, and Turing was robbed of the full reward for his originality. His paper, On Computable Numbers with an application to the Entscheidungsproblem, had to refer to Church's work, and was delayed until August 1936. However it was seen at the time that Turing's approach was original and different; Church relied upon an assumption internal to mathematics, rather than appealing to operations that could actually be done by real things or people in the physical world. Subsequently, the concept of the Turing machine has become the foundation of the modern theory of computation and computability. Turing worked in isolation from the powerful school of logical theory centred on Church at Princeton University, and his work emerged as that of a complete outsider. One can only speculate, but it looks as if Turing found in the concept of the Turing machine something that would satisfy the fascination with the problem of Mind that Christopher Morcom had sparked; his total originality lay in seeing the relevance of mathematical logic to a problem originally seen as one of physics. In this paper, as in so many aspects of his life, Turing made a bridge between the logical and the physical worlds, thought and action, which crossed conventional boundaries. His work introduced a concept of immense practical significance: the idea of the Universal Turing Machine. The concept of 'the Turing machine' is like that of 'the formula' or 'the equation'; there is an infinity of possible Turing machines, each corresponding to a different 'definite method' or algorithm. But imagine, as Turing did, each particular algorithm written out as a set of instructions in a standard form. Then the work of interpreting the instructions and carrying them out is itself a mechanical process, and so can itself be embodied in a particular Turing machine, namely the Universal Turing machine. A Universal Turing machine can be made do what any other particular Turing machine would do, by supplying it with the standard form describing that Turing machine. One machine, for all possible tasks. It is hard now not to think of a Turing machine as a computer program, and the mechanical task of interpreting and obeying the program as what the computer itself does. Thus, the Universal Turing Machine embodies the essential principle of the computer: a single machine which can be turned to any well-defined task by being supplied with the appropriate program. Additionally, the abstract Universal Turing Machine naturally exploits what was later seen as the 'stored program' concept essential to the modern computer: it embodies the crucial twentieth-century insight that symbols representing instructions are no different in kind from symbols representing numbers. But computers, in this modern sense, did not exist in 1936. Turing created these concepts out of his mathematical imagination. Only nine years later would electronic technology be tried and tested sufficiently to make it practical to transfer the logic of his ideas into actual engineering. In the meanwhile the idea lived only in his mind. In common with other outstanding young scientists, Turing spent two years at Princeton University enrolled as a graduate student. He arrived in September 1936. On Computable Numbers... was published at the very end of 1936 and attracted some attention; by the time he left, the idea had come to the attention of the leading Hungarian-American mathematician John von Neumann. But Turing certainly did not shoot to fame. He worked on on algebra and number theory; on showing that his definition of computability coincided with that of Church; and on an extension of his ideas (Ordinal Logics) which provided a Ph.D. thesis. The work on 'ordinal logics', probably his most difficult and deepest mathematical work, was an attempt to bring some kind of order to the realm of the uncomputable. This also was connected to the question of the nature of mind, as Turing's interpretation of his ideas suggested that human 'intuition' could correspond to uncomputable steps in an argument. But Turing never pursued this line of development after 1938. Instead, he was increasingly preoccupied with more immediate problems which demanded logical skills. True to the concreteness of the Turing machine, he also spent time at Princeton making a cipher machine based on using electromagnetic relays to multiply binary numbers. Even then he saw a link from 'useless' logic to practical computation. Although not one of the political intellectuals of the 1930s, Turing followed current events and was influenced in studying ciphers by the prospect of war with Germany. Copyright Andrew Hodges 1995, 1999 
http://plaslab.cis.nctu.edu.tw/max/turing/applet.html




三､Turing Test
The Turing Test
Who is Alan Turing?
Alan Turing (1912-1954) : famous British mathematician / logician, founder of computer science. He also helped cracked the German U-boat Enigma code in WWII. He was a homosexual and because of this was arrested in 1952 and put on trial. He resisted prison by submitting to humiliating treatment. He killed himself by eating an apple dipped in cyanide. You can find out more about his life from his biographer Andrew Hodges at http://www.turing.com/turing/Turing.html

What is the Turing test?
· In his 1950 paper "Computing Machinery and Intelligence", Turing proposed to consider the question "Can machines think?", and suggested that it should be replaced by the question of how machines will perform in an "imitation game". 
· Original version of the imitation game : judge talks to a man and woman through teletype and has to decide which is which. Turing asks : what if a machine takes the man's place? 
· Passing the Turing test = the judge cannot do better than guessing. Sometimes the Turing test is conceived as a simple test where a computer tries to deceive a judge into thinking that it is human. 
Does the Turing test aim to provide a definition of thinking or intelligence?
· It is sometimes suggested that the Turing test provides a (behavioural) definition of what thinking is, i.e. provides necessary and sufficient conditions for thinking. 
· But Turing said explicitly that he is not trying to give such a definition. Turing thought that the question of whether machines can think is "too meaningless to deserve discussion". 
· Even if we disregard what he said the definition would not be acceptable. 
1. Necessary? What about machines or creatures (e.g. babies) that can think but are not able to communicate with a language, or perhaps too shy or paranoid to do so? What if the judge is computer expert who can detect subtle hints? 
· Turing actually recognized an objection similar to the last point. He said that "we need not be troubled" as long as there are machines that can pass the test. This suggested that passing the test is not necessary for being able to think. 
1. Also, it is not sufficient. Who can be a judge? What if a computer passes the test because of a stupid judge? (Can we specify the criteria without bringing mentioning thinking or other mental concepts?) Or what about the unintelligent Blockhead? 
The Turing test as a practical criterion
· One way to think of the Turing test is that it is a practical test for thinking (Compare : determine how old a person is by his or her face), i.e. as a matter of fact, if something does pass the test then it can think. This does not mean that: 
1. the test enables us to define thinking (remember the Blockhead example), or 
2. that anything that thinks must be able to pass the test. 
· Is the test a good practical test? Depends on how likely it is that if something passes the test then it indeed can think. (John Searle argues that it is still a very poor test.) 
· But is it a useful test? Useful for what? 
1. Practical purposes? But the first batch of thinking machines would probably be ones that fail the Turing test, and if there are machines clever enough to pass the test, we'd probably do not need the test to be convinced that they can think anyway. 
2. Theoretical purposes? Passing the Turing test would be one goal of AI, but methodologically, to build a thinking machine, would it not be better to study the human mind instead of building a program to trick people? 

http://www.aaai.org/AITopics/html/turing.html
http://www.psych.ualberta.ca/~mike/Pearl_Street/OldDictionary/T/turing_test.html
http://www.ptproject.ilstu.edu/turing1.htm

四､AI Sites
http://www.futureai.com/articles/aisites.html
http://www.geneticprogramming.com/AI/fin.html
http://www.ets.uidaho.edu/ai/meetings.htm
http://www.ebi.ca/Links/AI_Sites/ai_sites.html
http://www-rcf.usc.edu/~oleary/IEEE_Expert/Locational/ai-com.htm
http://www.filmfodder.com/archive/general/050301.htm

五､AI Game
http://www.aiguru.com/
http://www.gamedev.net/columns/books/featuredbook.asp?productid=166
http://www.games-net.de/
http://www.rottentomatoes.com/games/
http://www.smartcomputing.com/editorial/article.asp?article=articles%2Farchive%2Fc0201%2F39c01%2F39c01b%2Easp
http://www.streetboards.com/aiapplets/universalbrain/universalbrain.html



六､心得：
看完Ａ﹒Ｉ的影片之後，機器人的語言處理､視覺､語音辦認､機器人的學習､專家系統及推論∼∼等都做的很好，人類在數十年間的研究雖然還在努力摸索中而技術上不是很成熟，但是以進步很快了。在還未看到Ａ﹒Ｉ這部片之前我已有看過數片有關Ａ﹒Ｉ的片子，但之中把機器人做的最好的是Ａ﹒Ｉ這部片子，因為他把人類的種種都有表現出來，讓我感到訝異的是那機器人付有感情､忌妒､追求某一件事物，做的真是太好了，希望這機器人快研發出來。