Coursera-吴恩达-深度学习-神经网络和深度学习-week1-测验

本文章内容：

Coursera吴恩达深度学习课程，第一课神经网络和深度学习Neural Networks and Deep Learning，

第一周：深度学习引言(Introduction to Deep Learning)

部分的测验，题目及答案截图。

正确:ABC

deep learning 已经在各个领域取得有效进展也是飞速加快的一个原因。

NN 不是一个新的领域，Neural Networks have been around for decades.

 

正确：ABD

C在图中，train大数据比小数据更慢。

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

RELU 函数会加快训练的速度。

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.

一个模型的关键是要有好的结果，经验是有用的，但也需要几次迭代才能build 一个好model。

 

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

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

D与题无关。

 

C正确Bringing more data to a model is almost always beneficial.大数据比小数据好，大数据几乎总是有益处的

D正确According to the trends in the figure above, big networks usually perform better than small networks.大网络比小网络好