推 gonzdevour:太感謝了。 07/03 00:45
※ 引述《gonzdevour (吞食)》之銘言:
: 我是學心靈哲學的,對電腦一竅不通。
: 想請問discrete和distributed這兩個詞的差異。
: 首先是Turing在Computing Machinery and Intelligence(1950)中,
: 談到神經系統與數位電腦的不同;
: "The nervous system is certainly not a discrete state machine.
: A small error in the information about the size of a nervous impulse
: impinging on a neuron may make a large difference to the size of the
: outgoing impulse. It may be argued that, this being so, one cannot
: expect to be able to mimic the behavior of the nervous system with
: a discrete state system."
: Turing也提到人腦是"continuous machine"(對比discrete state machine)。
: 而John Searle在與Dennett論戰的一篇文章中談數位電腦與類神經網路的區別:
: "A digital computer, the kind you are likely to buy in a store today,
: proceed by a series of steps performed very rapidly, millions per second.
: This is called a serial computer, and because the initial designs were
: by John von Neumann, it is sometimes called a von Neumann machine.
: Recently there have been efforts to build machines that operate in
: parallel, that is , with several computaional channels working at once
: and interacting with each other. In physical structure these are more
: like human brains. They are not really much like brains, but certainly
: they are more like brains than the traditional von Neumann machines.
: Computations of this type are called variously
: Parallel Distributed Processing, Neuronal Net Modeling, or simply
: Connectionism."
: 合這兩篇來看,
: 數位電腦又是discrete state machine, 又是serial machine,
: 類神經網又是parallel distributed machine, 又是continuous machine。
: 想請問:既然serial,為何又可以discrete?
: 既然continous, 為何又可以distributed?
: 謝謝。
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 59.105.140.133
數位電腦中的discrete所指的是數位電腦表達訊號的方式
是以電壓訊號High or Low的組合來表示訊號,而不是以連續的波型
數位電腦之所以稱為serial computer是因為它的運作方式是一次
處理一件事,循序執行.
可以想像做數學證明是一個一個步驟寫下去(有時間上的順序)
不能任意將兩個步驟交換,以確保整個過程正確.
特性通常我們能以數學方式的驗證數位電腦執行一項運算的正確性與執行時間.
然而處理複雜的問題則相當耗時.
神經系統distributed指的是神經系統的架構
是由許多神經元組成,神經元彼此之間有連結,並且能夠"獨立"完成簡單的運算
然後透過連結將結果傳給其他神經元.
可以把神經元想成一群人,其中某些人聽到一則新聞(資料輸入)
接著他們會把聽到的訊息加入自己的想法告訴其他人,
並且依據彼此關係的差異,同一個訊息透露給其他人的程度也不相同
(這個過程大家能同時進行,因此稱為平行處理)
最後由幾位代表做結論(資料輸出)
特性是能在短時間內輸出答案(平行處理的關係),不過得到的不是精確的答案.