雙語暢銷書《艾倫圖靈傳》第9章:退隱山林(100)
It would be a great convenience to say the least if the notation chosen were intelligible as mathematics when printed by the output ...
如果我們使用的語言能像數學語言那樣清晰，就會容易許多……
once the suitable notation is decided, all that would be necessary would be to type more or less ordinary mathematics and a special routine called, say, 'Programme' would convert this into the necessary instructions to make the machine carry out the operations indicated.
只要選好了適當的語言，接下來就只需要數學，以及一個特殊的程序，這個程序能把這種語言轉換成機器能夠識別的指令。
This may sound rather Utopian, but I think it, or something like it, should be possible, and I think it would open the way to making a simple learning programme.
這聽起來有點天方夜譚，但我相信這是可能的，而且這是實現機器學習的一個基礎。
I have not thought very seriously about this for long, but as soon as I have finished the Draughts programme I intend to have a shot at it.
我的想法還不是很嚴格，等我做完手頭的工作，我會認真研究一下。
He had been thinking about the learning process, not only in the classrooms of Harrow School, but by playing the logical game of Nim with a non-mathematical friend.
斯特拉齊對學習過程的思考，並不只在哈羅公學的教室裏，還在他與朋友玩取子游戲注的時候。
Most mathematicians would know from Rouse Ball's old Mathematical Recreations that there was an infallible rule for a winning strategy, based on expressing the number of matches in each heap in binary notation.
大部分數學家都知道，在《數學之樂》中，勞斯·鮑爾利用二進制來表示每堆火柴的數量，從而給出了一個必勝策略。
Few people were likely to spot this rule through play, but Strachey's friend did notice a special case of it, namely that a player who could achieve the position (n,n,0) had won, for thereafter it was only necessary to copy the opponent's moves to reduce the heaps down to (0,0,0).
沒有多少人能在遊戲時總結出這樣的策略，不過斯特拉齊的朋友卻發現了一個特殊情況，即只要能夠達到（n, n，0）這樣的局面，就肯定能贏，因爲在這之後，只需要一直模仿對手的取法，就能在最後使局面變成（0, 0，0）。
It was the element of abstraction achieved by a human learner that interested Strachey.
這是人類學習者得到的抽象想法，斯特拉齊覺得很有意思。
He had worked out a program which could keep a record of winning positions, and so improve its play by experience, but it could only store them individually, as (1,1,0), (2,2,0) and so on.
他編寫了一個程序，把所有的必勝局面記下來，從而根據經驗來提高勝率，但它只能離散而獨立地存儲這些局面，比如（1, 1，0）（2, 2，0）等。
This limitation soon allowed his novice friend to beat the program. Strachey wrote:
因爲這個侷限，他的朋友很快就擊敗了這個程序。斯特拉齊寫道：
This shows very clearly, I think, that one of the most important features of thinking is the ability to spot new relationships when presented with unfamiliar material...
我認爲這清楚地表明，思維的一個最重要的特徵，就是能在獨立的元素之間，找到新的聯繫……
and his Utopian 'Programme' was explained as one of his 'glimmerings of an idea as to how a machine might be made to do it.'
而他認爲他之前所說的那種程序，正是使機器能夠做到這一點的一個希望。
Alan's interests were by now centred on biology but he was still keen to develop such speculative ideas about mechanical thinking.
雖然圖靈現在主要的興趣是生物學，但他仍然喜歡琢磨關於機器學習的問題。
