Alan Turing

Alan Turing

1930: Death of friend Christopher Morcom

1931-34: Undergraduate at King's College, Cambridge University

1932-35: Studies quantum mechanics, probability, logic

1935: Elected fellow of King's College, Cambridge

1936: The Turing machine: On Computable Numbers... submitted

1936-38: At Princeton University. Ph.D. Papers in logic, algebra, number theory

1938-39: Return to Cambridge. Introduced to German Enigma cipher problem

1939-40 Devises the Bombe, machine for Enigma decryption

1939-42: Breaking of U-boat Enigma cipher, saving battle of the Atlantic

1943-45: Chief Anglo-American consultant. Introduced to electronics

1945: National Physical Laboratory, London

1946: Computer design, leading the world, formally accepted

1947-48: Papers on programming, neural nets, and prospects for artificial intelligence

1948: Manchester University

1949: Work on programming and world's first serious use of a computer

1950: Philosophical paper on machine intelligence: the Turing Test

1951: Elected FRS. Paper on non-linear morphogenesis theory

1952: Arrested and tried as a homosexual, loss of security clearance

1953-54: Unfinished work in biology and physics

1954 (7 June): Death by cyanide poisoning, Wilmslow, Cheshire 

Turing Machine

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》

Turing Test

杜寧測試 (Turing Test)：1951年杜寧(Alan Turing)提出有名的「杜寧測試」來測試一部機器是否具智慧，也是判斷機器是否具有智慧最為人熟知的方法。杜寧測試的方法有許多的版本，基本上其原理與方法是：假設有三個房間，有一個房間裡面坐著一個人，另一個房間有一部具有「人工智慧」的機器，而你坐在第三個房間，假設你能透過鍵盤、螢幕或甚至聲音與其他兩個房間溝通。你能隨意決定談話的時間、談話的內容並提出各種問題。但是記住另外一個房間的「人」會想盡辦法，讓你誤認他是一部「機器」；相反的來自另一個房間的「機器」想盡辦法，要你相信他是一個「人」，在經過適當的溝通與對話後，你必須決定剛剛談話的對象，那一個房間是人，那一個房間是機器。假如你無法辨認或誤判「機器」是人，則這部機器通過杜寧測試而具有智慧。杜寧測試雖然在1951年就被提出來，但是直到1991年才有一位熱衷於人工智慧的洛布納(Hugh Loebner)博士，提供十萬美元給通過杜寧測試的機器設計者，舉辦叫洛布納獎的杜寧測試比賽，才開始有機器挑戰杜寧測試。直到目前為止，還沒有任何一部機器通過杜林測試。目前的機器離這個境界還很遙遠，因此，洛布納獎每年只頒發一千五百美元獎金獎勵最接近人工智慧的機器。–––明志技術學院林榮泰

Turing Award

Turing Award 號稱是電腦科學界的 Nobel prize, 此獎項紀念在電腦理論基礎做出卓越貢獻的英國科學家 Alan Turing(1912-1954), 他也在二戰中破解著名的德國密碼機(Enigma), 而享譽國際.

Turing Award 對得獎者條件要求極高, 審查程序極嚴格, 一般都要在其領域上做出傑出貢獻的才有可能獲獎, 如眾所周知的,

1, 發明Hamming code 的 Richard Hamming
2, AI 大師 Marvin Minsky , John McCarthy.
3, 寫 The Art of Computer Programming 三本書及發明 Tex 的 Donald Knuth
4, 關於結構化程式語言的 E.W. Dijkstra
5, 發明 Unix 和 C 的Ken Thompson 和 Dennis Ritchie
6, 發現 NP-complete 的 Steven Cook 和推廣結果的 Richard Karp
7, 發現隨機式演算法(Randomized Algorithm)的 Michael Rabin
...etc.

http://aimovie.warnerbros.com/html/flash.html

l          Empire Earth→世紀爭霸

l          Age Of Empire→世紀帝國

l          Command & Conquer: Red Alert 2™→終極動員令：紅色警戒Ⅱ

        原本以為說上這一門“人工智慧概論”會學到非常多的「理論課程」，但想不到有上機課，竟也有「網頁作業」，一下子不太習慣。當然，同時也對以往懵懵懂懂的“A.I.”有了更進一步的認知，但也許是做學生的悲衰吧？上理論課總是不知不覺的覺得疲倦、眼皮漸重，或許我對這門課還不夠熱愛吧？

        這次的作業，說實在獲得最多的，就是發現到與科學界相較之下，有一座與諾貝爾獎不相上下的榮譽–杜寧獎，及對於人工智慧領域相關的一切的一切，這倒是吸引我更多，也更強烈的灌輸給我一種由好奇心所延展出來的莫名感覺，感受很新奇、很特別，好似冒險家發現天外境地般，使人雀躍，但不知是杜寧獎的曝光度不如諾貝爾獎，使得我找不到頭緒去探索它，怪不得「它」會成為一個作業…。