1. 程式人生 > >Coursera-吳恩達-深度學習-神經網路和深度學習-week1-測驗

Coursera-吳恩達-深度學習-神經網路和深度學習-week1-測驗

本文章內容:

Coursera吳恩達深度學習課程,第一課神經網路和深度學習Neural Networks and Deep Learning,

第一週:深度學習引言(Introduction to Deep Learning)

部分的測驗,題目及答案截圖。

正確:ABC

deep learning 已經在各個領域取得有效進展也是飛速加快的一個原因。

NN 不是一個新的領域,Neural Networks have been around for decades.

 

正確:ABD

C在圖中,train大資料比小資料更慢。

D正確,

For example, we discussed how switching from sigmoid to ReLU activation functions allows faster training.

RELU 函式會加快訓練的速度。

Finding the characteristics of a model is key to have good performance. Although experience can help, it requires multiple iterations to build a good model.

一個模型的關鍵是要有好的結果,經驗是有用的,但也需要幾次迭代才能build 一個好model。

 

A正確,We can train it on many pairs of sentences x (English) and y (French).

C正確,An RNN can map from a sequence of english words to a sequence of french words.

D與題無關。

 

C正確Bringing more data to a model is almost always beneficial.大資料比小資料好,大資料幾乎總是有益處的

D正確According to the trends in the figure above, big networks usually perform better than small networks.

大網路比小網路好