回頭接著學(xué)習(xí)深度學(xué)習(xí)基礎(chǔ)窃诉，推薦個很好的online book:http://neuralnetworksanddeeplearning.com/chap4.html,該章主要圖形化的展示了為什么神經(jīng)網(wǎng)絡(luò)可以用來表示任何函數(shù)。有一句話很有意思，But it's worth reminding ourselves: the ability to compute an arbitrary function is truly remarkable. Almost any process you can imagine can be thought of as function computation.我所能夠想象的任何過程都能被表示成為函數(shù)俐东，什么樣的問題不能表示為函數(shù)呢缩宜？也就是說什么樣的問題不能用深度學(xué)習(xí)方法來解決呢吊履？？回歸到基礎(chǔ)數(shù)學(xué)氛雪，什么是函數(shù)。來我們看看:
[for every element in input set(just collections, ex: a set of clothes), we have exactly one output element[single valued]. This is the difference between function and relation.]
A function can then be defined as a?set?of ordered pairs,?"if it contains (a, b) and (a, c), then b must equal c"[single valued].
