深度學習與神經網絡習題（1）

       最近在學習網易雲課堂上吳恩達教授的《神經網絡與深度學習》的課程，作了第一週的測試題，沒有答案，因而想分享本身的參考解析（根據coursera 榮譽準則不容許公佈答案），以供討論。

1。What does the analogy 「AI is the new electricity」 refer to?

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

B. Through the 「smart grid」, AI is delivering a new wave of electricity.

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

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

個人解析：AI是一種新的生產力，就像100年前的電的出現同樣，帶動了不少工業的發展。

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

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

B. We have access to a lot more data.

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

D. Neural Networks are a brand new field.

個人解析：視頻中老師講到，第三節的文檔材料中以下圖所示，闡述的是數據、計算速度、算法都是深度學習的興原由素。

 

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

 

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).

個人解析：數據、計算、算法

 

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?

個人解析：一位有經驗的深度學習工程師能夠基於以前的問題來選擇問題適合的模型，而不用在模型上迭代不少次，就好比說CNN相比於其餘模型來講更適用圖像識別等，那麼再遇到一個新的問題時，好比無人駕駛的問題，就可使用CNN來處理圖像。

5。Which one of these plots represents a ReLU activation function?

個人解析：

 

6。Images for cat recognition is an example of 「structured」 data, because it is represented as a structured array in a computer. True/False?

個人解析：音頻、圖像、文本都是非結構化數據。

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?

個人解析：像統計數據這些有明肯定義的數據是結構化數據。

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

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->....

個人解析：RNN適合機器翻譯，緣由是機器翻譯是做爲監督學習問題處理，並RNN算法更適合處理序列化的數據。

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

A. x-axis is the performance of the algorithm

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

B. x-axis is the input to the algorithm

y-axis is outputs.

C. x-axis is the amount of data

y-axis is the size of the model you train.

D. x-axis is the amount of data

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

個人解析：

 

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

個人解析：」Scale drives deep learning progress.」根據第9題的圖也能夠得出如下結論——不管是增長數據的規模仍是神經網絡的規模都不會下降算法的表現，有時會有顯著做用。