課程一(Neural Networks and Deep Learning)，第一週（Introduction to Deep Learning）—— 2、10個測驗題
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.
----------------------------------------中文翻譯----------------------------------------------
1、"AI 是新電" 的比喻是指什麼？（B）
A、通過 "智慧電網", AI 正在提供一個新的電力浪潮。
B、類似於100年前開始的電力, AI 正在轉變多個產業。
C、AI 正在我們的家庭和辦公室為個人裝置供電, 類似於電力。
D、AI 執行在計算機上, 因此是由電力驅動的, 但它是讓計算機做的事情之前不可能。
2、哪些是最近才開始學習的原因？(請檢查適用的三選項）（A、B、D）
A、我們可以獲得更多的資料。
B、我們可以獲得更多的計算能力。
C、神經網路是一個嶄新的領域。
D、深入的學習已導致重要的應用, 如線上廣告, 語音識別和影象識別的重大改進。
3、回想一下關於不同 ML 思想的迭代圖。下面哪個陳述是真的？(檢查所有適用的） （A、B、D）
A、能夠快速地試用想法,可以讓深學習的工程師更快地進行迭代。
B、更快的計算,可以幫助加快團隊迭代到一個好的想法的時間。
C、在大資料集上訓練比小資料集更快。
D、在深入學習演算法的最新進展使我們能夠更快地訓練好的模型 (即使不改變 CPU/GPU 硬體)。
4、當一個經驗豐富的深學習工程師在一個新的問題上工作時, 他們通常可以利用以前的問題的洞察力, 在第一次嘗試中訓練一個好的模型, 而不需要通過不同的模型多次迭代。真/假？ （B）
A、真
B、假
5、這些圖形中的哪一個代表一個 ReLU 啟用函式？ （C）
A. Figure 1:
B. Figure 2:
C. Figure 3:
D.Figure4
6、用於 cat 識別的影象是 "結構化" 資料的一個示例, 因為它在計算機中表示為結構化陣列。真/假？（B）
A、真
B、假
7、一個人口統計資料集在不同城市的人口, 人均 GDP, 經濟增長是一個 "非結構化" 資料的例子, 因為它包含來自不同來源的資料。真/假？ （B）
A、真
B、假
8、為什麼 RNN (遞迴神經網路) 用於機器翻譯, 說將英語翻譯成法語？(檢查所有適用的）（A、C）
A、它可以被訓練作為一個被監督的學習問題。
B、它是嚴格比卷積神經網路 (CNN) 更強大。
C、當輸入/輸出是一個序列 (例如, 一個單詞序列) 時, 它是適用的。
D、RNNs 代表了思想的反覆過程->> 程式碼->> 實驗->> 想法...。
9、
在我們在講座中手繪的圖表中, 水平軸 (x 軸) 和垂直軸 (y-axis) 代表什麼？（A）
A、
x 軸是資料量
y-axis (縱軸) 是該演算法的效能。
B、
x 軸是演算法的效能
y-axis (垂直軸) 是資料量。
C、
x 軸是資料量
y-axis 是你訓練的模型的大小。
D、
x 軸是演算法的輸入
y-axis 是輸出。
10、假設前一個問題的圖中描述的趨勢是準確的 (並希望你得到了座標軸標籤), 下面哪一個是正確的？(檢查所有適用的）（A、C）
A、增加神經網路的大小通常不會損害演算法的效能, 而且可能有很大的幫助。
B、減小神經網路的大小通常不會影響演算法的效能, 而且可能會有明顯的幫助。
C、增加訓練集的大小通常不會影響演算法的效能, 而且可能有很大的幫助。
D、降低訓練集的大小通常不會影響演算法的效能, 而且可能會有明顯的幫助。