课程一(Neural Networks and Deep Learning)，第一周（Introduction to Deep Learning）—— 2、10个测验题

1、What does the analogy “AI is the new electricity” refer to?  (B)

A. Through the “smart grid”, AI is delivering a new wave of electricity.

B. Similar to electricity starting about 100 years ago, AI is transforming multiple industries.

C. AI is powering personal devices in our homes and offices, similar to electricity.

D. AI runs on computers and is thus powered by electricity, but it is letting computers do things not possible before.

2、Which of these are reasons for Deep Learning recently taking off? (Check the three options that apply.)  (A、B、D)

A. We have access to a lot more data.

B. We have access to a lot more computational power.

C. Neural Networks are a brand new field.

D. Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.

 

3、Recall this diagram of iterating over different ML ideas. Which of the statements below are true? (Check all that apply.) (A、B、D)

A. Being able to try out ideas quickly allows deep learning engineers to iterate more quickly.

B. Faster computation can help speed up how long a team takes to iterate to a good idea.

C. It is faster to train on a big dataset than a small dataset.

D. Recent progress in deep learning algorithms has allowed us to train good models faster (even without changing the CPU/GPU hardware).

4、When an experienced deep learning engineer works on a new problem, they can usually use insight from previous problems to train a good model on the first try, without needing to iterate multiple times through different models. True/False?  (B)

A. True

B. False

5、Which one of these plots represents a ReLU activation function? (C)

A. Figure 1:

B. Figure 2:

C. Figure 3:

D.Figure4

6.Images for cat recognition is an example of “structured” data, because it is represented as a structured array in a computer. True/False? (B)

A. True

B. False

7.A demographic dataset with statistics on different cities' population, GDP per capita, economic growth is an example of “unstructured” data because it contains data coming from different sources. True/False?(B)

A. True

B. False

8.Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.) (A、C)

A. It can be trained as a supervised learning problem.

B. It is strictly more powerful than a Convolutional Neural Network (CNN).

C. It is applicable when the input/output is a sequence (e.g., a sequence of words).

D. RNNs represent the recurrent process of Idea->Code->Experiment->Idea->....

9.In this diagram which we hand-drew in lecture, what do the horizontal axis (x-axis) and vertical axis (y-axis) represent? (A)

A.

x-axis is the amount of data
y-axis (vertical axis) is the performance of the algorithm.

B.

x-axis is the performance of the algorithm
y-axis (vertical axis) is the amount of data.

C.

x-axis is the amount of data
y-axis is the size of the model you train.

D.

x-axis is the input to the algorithm
y-axis is outputs.

10.Assuming the trends described in the previous question's figure are accurate (and hoping you got the axis labels right), which of the following are true? (Check all that apply.) (A、C)

A. Increasing the size of a neural network generally does not hurt an algorithm’s performance, and it may help significantly.

B. Decreasing the size of a neural network generally does not hurt an algorithm’s performance, and it may help significantly.

C. Increasing the training set size generally does not hurt an algorithm’s performance, and it may help significantly.

D. Decreasing the training set size generally does not hurt an algorithm’s performance, and it may help significantly.

----------------------------------------中文翻译----------------------------------------------

1、"AI 是新电" 的比喻是指什么？（B）

A、通过 "智能电网", AI 正在提供一个新的电力浪潮。

B、类似于100年前开始的电力, AI 正在转变多个产业。

C、AI 正在我们的家庭和办公室为个人设备供电, 类似于电力。

D、AI 运行在计算机上, 因此是由电力驱动的, 但它是让计算机做的事情之前不可能。

 

2、哪些是最近才开始学习的原因？(请检查适用的三选项）（A、B、D）

A、我们可以获得更多的数据。

B、我们可以获得更多的计算能力。

C、神经网络是一个崭新的领域。

D、深入的学习已导致重要的应用, 如在线广告, 语音识别和图像识别的重大改进。

 

3、回想一下关于不同 ML 思想的迭代图。下面哪个陈述是真的？(检查所有适用的） （A、B、D）

A、能够快速地试用想法,可以让深学习的工程师更快地进行迭代。

B、更快的计算,可以帮助加快团队迭代到一个好的想法的时间。

C、在大数据集上训练比小数据集更快。

D、在深入学习算法的最新进展使我们能够更快地训练好的模型 (即使不改变 CPU/GPU 硬件)。

 

4、当一个经验丰富的深学习工程师在一个新的问题上工作时, 他们通常可以利用以前的问题的洞察力, 在第一次尝试中训练一个好的模型, 而不需要通过不同的模型多次迭代。真/假？ （B）

A、真

B、假

 

5、这些图形中的哪一个代表一个 ReLU 激活函数？ （C）

A. Figure 1:

B. Figure 2:

C. Figure 3:

D.Figure4

6、用于 cat 识别的图像是 "结构化" 数据的一个示例, 因为它在计算机中表示为结构化数组。真/假？（B）

A、真 

B、假

 

7、一个人口统计数据集在不同城市的人口, 人均 GDP, 经济增长是一个 "非结构化" 数据的例子, 因为它包含来自不同来源的数据。真/假？ （B）

A、真

B、假

8、为什么 RNN (递归神经网络) 用于机器翻译, 说将英语翻译成法语？(检查所有适用的）（A、C）

A、它可以被训练作为一个被监督的学习问题。

B、它是严格比卷积神经网络 (CNN) 更强大。

C、当输入/输出是一个序列 (例如, 一个单词序列) 时, 它是适用的。

D、RNNs 代表了思想的反复过程->> 代码->> 实验->> 想法...。

9、

在我们在讲座中手绘的图表中, 水平轴 (x 轴) 和垂直轴 (y-axis) 代表什么？（A）

A、

x 轴是数据量

y-axis (纵轴) 是该算法的性能。

B、

x 轴是算法的性能

y-axis (垂直轴) 是数据量。

C、

x 轴是数据量

y-axis 是你训练的模型的大小。

D、

x 轴是算法的输入

y-axis 是输出。

 

10、假设前一个问题的图中描述的趋势是准确的 (并希望你得到了坐标轴标签), 下面哪一个是正确的？(检查所有适用的）（A、C）

A、增加神经网络的大小通常不会损害算法的性能, 而且可能有很大的帮助。

B、减小神经网络的大小通常不会影响算法的性能, 而且可能会有明显的帮助。

C、增加训练集的大小通常不会影响算法的性能, 而且可能有很大的帮助。

D、降低训练集的大小通常不会影响算法的性能, 而且可能会有明显的帮助。

 

----------------------------------------------------------------------------------------------------------------------

以上答案仅供参考