【中英】【吳恩達課後測驗】Course 1 - 神經網絡和深度學習 - 第一週測驗
第一週測驗 - 深度學習簡介
和“AI是新電力”相類似的說法是什麼？
- 【 】AI爲我們的家庭和辦公室的個人設備供電，類似於電力。
- 【 】通過“智能電網”，AI提供新的電能。
- 【 】AI在計算機上運行，並由電力驅動，但是它正在讓以前的計算機不能做的事情變爲可能。
- 【
★】就像100年前產生電能一樣，AI正在改變很多的行業。
請注意: 吳恩達在視頻中表達了同樣的觀點。
哪些是深度學習快速發展的原因？ (兩個選項)
- 【
★】 現在我們有了更好更快的計算能力。 - 【 】神經網絡是一個全新的領域。
- 【
★】 我們現在可以獲得更多的數據。 - 【 】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。
- 【
回想一下關於不同的機器學習思想的迭代圖。下面哪(個/些)陳述是正確的？
- 【
★】能夠讓深度學習工程師快速地實現自己的想法。 - 【
★】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。 - 【 】在數據量很多的數據集上訓練上的時間要快於小數據集。
- 【
★】 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）。
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。
- 【
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？
- 【 】正確
- 【
★】 錯誤
請注意：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。
這些圖中的哪一個表示ReLU激活功能？
- 點擊這裏.
博主注：沒有搞到圖，只好放一張正確的圖。
- 點擊這裏.
用於識別貓的圖像是“結構化”數據的一個例子，因爲它在計算機中被表示爲結構化矩陣，是真的嗎？
- 【 】正確
- 【
★】 錯誤
博主注：圖片屬於非結構化數據。
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，因爲它包含來自不同來源的數據，是真的嗎？
- 【 】正確
- 【
★】 錯誤
博主注：單純的看以上數據的話就是非結構化數據，但是這些數據都被整合到了數據集裏面，所以是結構化數據。
爲什麼在上RNN（循環神經網絡）可以應用機器翻譯將英語翻譯成法語？
- 【
★】 因爲它可以被用做監督學習。 - 【 】嚴格意義上它比卷積神經網絡（CNN）效果更好。
- 【
★】 它比較適合用於當輸入/輸出是一個序列的時候（例如：一個單詞序列） - 【 】RNNs代表遞歸過程：想法->編碼->實驗->想法->…
- 【
.在我們手繪的這張圖中，橫軸（x軸）和縱軸（y軸）代表什麼?
- x軸是數據量
- y軸（垂直軸）是算法的性能
假設上一個問題圖中描述的是準確的（並且希望您的軸標籤正確），以下哪一項是正確的?
- 【
★】 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。 - 【
★】 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。 - 【 】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。
- 【 】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。
- 【
Week 1 Quiz - Introduction to deep learning
What does the analogy “AI is the new electricity” refer to?
- [ ]AI is powering personal devices in our homes and offices, similar to electricity.
- [ ]Through the “smart grid”, AI is delivering a new wave of electricity.
- [ ]AI runs on computers and is thus powered by electricity, but it is letting computers do things not possible before.
- [x]Similar to electricity starting about 100 years ago, AI is transforming multiple industries.
Note: Andrew illustrated the same idea in the lecture.
Which of these are reasons for Deep Learning recently taking off? (Check the two options that apply.)
- [x] We have access to a lot more computational power.
- [ ]Neural Networks are a brand new field.
- [x] We have access to a lot more data.
- [ ]Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.
Recall this diagram of iterating over different ML ideas. Which of the statements below are true? (Check all that apply.)
- [x] Being able to try out ideas quickly allows deep learning engineers to iterate more quickly.
- [x] Faster computation can help speed up how long a team takes to iterate to a good idea.
- [ ]It is faster to train on a big dataset than a small dataset.
- [x] Recent progress in deep learning algorithms has allowed us to train good models faster (even without changing the CPU/GPU hardware).
Note: A bigger dataset generally requires more time to train on a same model.
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?
- [ ]True
- [x] False
Note: Maybe some experience may help, but nobody can always find the best model or hyperparameters without iterations.
Which one of these plots represents a ReLU activation function?
- Check here.
Images for cat recognition is an example of “structured” data, because it is represented as a structured array in a computer. True/False?
- [ ]True
- [x] False
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?
- [ ]True
- [x] False
Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.)
- [x] It can be trained as a supervised learning problem.
- [ ]It is strictly more powerful than a Convolutional Neural Network (CNN).
- [x] It is applicable when the input/output is a sequence (e.g., a sequence of words).
- [ ]RNNs represent the recurrent process of Idea->Code->Experiment->Idea->….
In this diagram which we hand-drew in lecture, what do the horizontal axis (x-axis) and vertical axis (y-axis) represent?
- x-axis is the amount of data
- y-axis (vertical axis) is the performance of the algorithm.
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.)
- [x] Increasing the training set size generally does not hurt an algorithm鈥檚 performance, and it may help significantly.
- [x] Increasing the size of a neural network generally does not hurt an algorithm鈥檚 performance, and it may help significantly.
- [ ]Decreasing the training set size generally does not hurt an algorithm鈥檚 performance, and it may help significantly.
- [ ]Decreasing the size of a neural network generally does not hurt an algorithm鈥檚 performance, and it may help significantly.