導語

本文翻譯自deeplearning.ai的深度學習課程測試作業，近期將逐步翻譯完畢，一共五門課。

翻譯：黃海廣

本集翻譯Lesson1 Week 1：

Lesson1 Neural Networks and Deep Learning (第一門課 神經網絡和深度學習)

Week 1 Quiz - Introduction to deep learning(第一周測驗 - 深度學習簡介)

1. What does the analogy “AI is the new electricity” refer to?(和“AI是新電力”相類似的說法是什么？)

【 】AI is powering personal devices in our homes and offices, similar to electricity.(AI為我們的家庭和辦公室的個人設備供電，類似于電力。)

【 】Through the “smart grid”, AI is delivering a new wave of electricity.(通過“智能電網”，AI提供新的電能。)

【 】AI runs on computers and is thus powered by electricity, but it is letting computers do things not possible before.(AI在計算機上運行，并由電力驅動，但是它正在讓以前的計算機不能做的事情變為可能。)

【★】Similar to electricity starting about 100 years ago, AI is transforming multiple industries.(就像100年前產生電能一樣，AI正在改變很多的行業。)

Note: Andrew illustrated the same idea in the lecture.(注: 吳恩達在視頻中表達了同樣的觀點。)

2. Which of these are reasons for Deep Learning recently taking off? (Check the two options that apply.)(哪些是深度學習快速發展的原因？(兩個選項))

【★】 We have access to a lot more computational power.(現在我們有了更好更快的計算能力。)

【 】Neural Networks are a brand new field.(神經網絡是一個全新的領域。)

【★】 We have access to a lot more data.(我們現在可以獲得更多的數據。)

【 】Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.(深度學習已經取得了重大的進展，比如在在線廣告、語音識別和圖像識別方面有了很多的應用。)

3. Recall this diagram of iterating over different ML ideas. Which of the statements below are true? (Check all that apply.)(回想一下關于不同的機器學習思想的迭代圖。下面哪(個/些)陳述是正確的？)

【★】Being able to try out ideas quickly allows deep learning engineers to iterate more quickly.(能夠讓深度學習工程師快速地實現自己的想法。)

【★】Faster computation can help speed up how long a team takes to iterate to a good idea.(在更好更快的計算機上能夠幫助一個團隊減少迭代(訓練)的時間。)

【 】It is faster to train on a big dataset than a small dataset.(在數據量很多的數據集上訓練上的時間要快于小數據集。)

【★】Recent progress in deep learning algorithms has allowed us to train good models faster (even without changing the CPU/GPU hardware).(使用更新的深度學習算法可以使我們能夠更快地訓練好模型（即使更換CPU /GPU硬件）。)

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

( 請注意: 同一模型在較大的數據集上通常需要花費更多時間。)

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?( 當一個經驗豐富的深度學習工程師在處理一個新的問題的時候，他們通常可以利用先前的經驗來在第一次嘗試中訓練一個表現很好的模型，而不需要通過不同的模型迭代多次從而選擇一個較好的模型，這個說法是正確的嗎？)

【 】True(正確)

【★】 False(錯誤)

Note: Maybe some experience may help, but nobody can always find the best model or hyperparameters without iterations.(注：也許之前的一些經驗可能會有所幫助，但沒有人總是可以找到最佳模型或超參數而無需迭代多次。)

5. Which one of these plots represents a ReLU activation function? (這些圖中的哪一個表示ReLU激活功能？)

Answer(回答)：

【 】True(正確)

6. Images for cat recognition is an example of “structured” data, because it is represented as a structured array in a computer. True/False?(用于識別貓的圖像是“結構化”數據的一個例子，因為它在計算機中被表示為結構化矩陣，是真的嗎？)

【 】True(正確)

【★】 False(錯誤)

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? (統計不同城市人口、人均GDP、經濟增長的人口統計數據集是“非結構化”數據的一個例子，因為它包含來自不同來源的數據，是真的嗎？)

【 】True(正確)

【★】 False(錯誤)

8. Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.)(為什么在上RNN（循環神經網絡）可以應用機器翻譯將英語翻譯成法語？)

【★】It can be trained as a supervised learning problem. (因為它可以被用做監督學習。)

【 】It is strictly more powerful than a Convolutional Neural Network (CNN).(嚴格意義上它比卷積神經網絡（CNN）效果更好。)

【★】It is applicable when the input/output is a sequence (e.g., a sequence of words). (它比較適合用于當輸入/輸出是一個序列的時候（例如：一個單詞序列）)

【 】RNNs represent the recurrent process of Idea->Code->Experiment->Idea->….(RNNs代表遞歸過程：想法->編碼->實驗->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?(在我們手繪的這張圖中，橫軸（x軸）和縱軸（y軸）代表什么? )

Answer(回答):

x-axis is the amount of data(x軸是數據量)

y-axis (vertical axis) is the performance of the algorithm.(y軸（垂直軸）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.) (假設上一個問題圖中描述的是準確的（并且希望您的軸標簽正確），以下哪一項是正確的?

【★】Increasing the training set size generally does not hurt an algorithm performance, and it may help significantly. (增加訓練集的大小通常不會影響算法的性能，這可能會有很大的幫助。)

【★】 Increasing the size of a neural network generally does not hurt an algorithm performance, and it may help significantly.(增加神經網絡的大小通常不會影響算法的性能，這可能會有很大的幫助。)

【 】Decreasing the training set size generally does not hurt an algorithm performance, and it may help significantly.(減小訓練集的大小通常不會影響算法的性能，這可能會有很大的幫助。)

【 】Decreasing the size of a neural network generally does not hurt an algorithm performance, and it may help significantly.(減小神經網絡的大小通常不會影響算法的性能，這可能會有很大的幫助。)

備注：公眾號菜單包含了整理了一本AI小抄，非常適合在通勤路上用學習。

往期精彩回顧2019年公眾號文章精選適合初學者入門人工智能的路線及資料下載機器學習在線手冊深度學習在線手冊AI基礎下載（第一部分）備注：加入本站微信群或者qq群，請回復“加群”加入知識星球（4500+用戶，ID：92416895），請回復“知識星球”

喜歡文章，點個在看

總結

以上是生活随笔為你收集整理的原文翻译：深度学习测试题（L1 W1 测试题）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。