导语

本文翻译自deeplearning.ai的深度学习课程测试作业，近期将逐步翻译完毕，一共五门课。

翻译：黄海广

本集翻译Lesson1 Week 1：

Lesson1 Neural Networks and Deep Learning (第一门课 神经网络和深度学习)

Week 1 Quiz - Introduction to deep learning(第一周测验 - 深度学习简介)

1. What does the analogy “AI is the new electricity” refer to?(和“AI是新电力”相类似的说法是什么？)

【 】AI is powering personal devices in our homes and offices, similar to electricity.(AI为我们的家庭和办公室的个人设备供电，类似于电力。)

【 】Through the “smart grid”, AI is delivering a new wave of electricity.(通过“智能电网”，AI提供新的电能。)

【 】AI runs on computers and is thus powered by electricity, but it is letting computers do things not possible before.(AI在计算机上运行，并由电力驱动，但是它正在让以前的计算机不能做的事情变为可能。)

【★】Similar to electricity starting about 100 years ago, AI is transforming multiple industries.(就像100年前产生电能一样，AI正在改变很多的行业。)

Note: Andrew illustrated the same idea in the lecture.(注: 吴恩达在视频中表达了同样的观点。)

2. Which of these are reasons for Deep Learning recently taking off? (Check the two options that apply.)(哪些是深度学习快速发展的原因？(两个选项))

【★】 We have access to a lot more computational power.(现在我们有了更好更快的计算能力。)

【 】Neural Networks are a brand new field.(神经网络是一个全新的领域。)

【★】 We have access to a lot more data.(我们现在可以获得更多的数据。)

【 】Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.(深度学习已经取得了重大的进展，比如在在线广告、语音识别和图像识别方面有了很多的应用。)

3. Recall this diagram of iterating over different ML ideas. Which of the statements below are true? (Check all that apply.)(回想一下关于不同的机器学习思想的迭代图。下面哪(个/些)陈述是正确的？)

【★】Being able to try out ideas quickly allows deep learning engineers to iterate more quickly.(能够让深度学习工程师快速地实现自己的想法。)

【★】Faster computation can help speed up how long a team takes to iterate to a good idea.(在更好更快的计算机上能够帮助一个团队减少迭代(训练)的时间。)

【 】It is faster to train on a big dataset than a small dataset.(在数据量很多的数据集上训练上的时间要快于小数据集。)

【★】Recent progress in deep learning algorithms has allowed us to train good models faster (even without changing the CPU/GPU hardware).(使用更新的深度学习算法可以使我们能够更快地训练好模型（即使更换CPU /GPU硬件）。)

Note: A bigger dataset generally requires more time to train on a same  model.

( 请注意: 同一模型在较大的数据集上通常需要花费更多时间。)

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?( 当一个经验丰富的深度学习工程师在处理一个新的问题的时候，他们通常可以利用先前的经验来在第一次尝试中训练一个表现很好的模型，而不需要通过不同的模型迭代多次从而选择一个较好的模型，这个说法是正确的吗？)

【 】True(正确)

【★】 False(错误)

Note: Maybe some experience may help, but nobody can always find the best model or hyperparameters without iterations.(注：也许之前的一些经验可能会有所帮助，但没有人总是可以找到最佳模型或超参数而无需迭代多次。)

5. Which one of these plots represents a ReLU activation function? (这些图中的哪一个表示ReLU激活功能？)

Answer(回答)：

【 】True(正确)

6. Images for cat recognition is an example of “structured” data, because it is represented as a structured array in a computer. True/False?(用于识别猫的图像是“结构化”数据的一个例子，因为它在计算机中被表示为结构化矩阵，是真的吗？)

【 】True(正确)

【★】 False(错误)

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? (统计不同城市人口、人均GDP、经济增长的人口统计数据集是“非结构化”数据的一个例子，因为它包含来自不同来源的数据，是真的吗？)

【 】True(正确)

【★】 False(错误)

8. Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.)(为什么在上RNN（循环神经网络）可以应用机器翻译将英语翻译成法语？)

【★】It can be trained as a supervised learning problem. (因为它可以被用做监督学习。)

【 】It is strictly more powerful than a Convolutional Neural Network (CNN).(严格意义上它比卷积神经网络（CNN）效果更好。)

【★】It is applicable when the input/output is a sequence (e.g., a sequence of words). (它比较适合用于当输入/输出是一个序列的时候（例如：一个单词序列）)

【 】RNNs represent the recurrent process of Idea->Code->Experiment->Idea->….(RNNs代表递归过程：想法->编码->实验->想法->…)

9. In this diagram which we hand-drew in lecture, what do the horizontal axis (x-axis) and vertical axis (y-axis) represent?(在我们手绘的这张图中，横轴（x轴）和纵轴（y轴）代表什么? )

Answer(回答):

x-axis is the amount of data(x轴是数据量)

y-axis (vertical axis) is the performance of the algorithm.(y轴（垂直轴）是算法的性能)

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.) (假设上一个问题图中描述的是准确的（并且希望您的轴标签正确），以下哪一项是正确的?

【★】Increasing the training set size generally does not hurt an algorithm performance, and it may help significantly. (增加训练集的大小通常不会影响算法的性能，这可能会有很大的帮助。)

【★】 Increasing the size of a neural network generally does not hurt an algorithm performance, and it may help significantly.(增加神经网络的大小通常不会影响算法的性能，这可能会有很大的帮助。)

【 】Decreasing the training set size generally does not hurt an algorithm performance, and it may help significantly.(减小训练集的大小通常不会影响算法的性能，这可能会有很大的帮助。)

【 】Decreasing the size of a neural network generally does not hurt an algorithm performance, and it may help significantly.(减小神经网络的大小通常不会影响算法的性能，这可能会有很大的帮助。)

备注：公众号菜单包含了整理了一本AI小抄，非常适合在通勤路上用学习。

往期精彩回顾




2019年公众号文章精选适合初学者入门人工智能的路线及资料下载机器学习在线手册深度学习在线手册AI基础下载（第一部分）备注：加入本站微信群或者qq群，请回复“加群”加入知识星球（4500+用户，ID：92416895），请回复“知识星球”

喜欢文章，点个在看