Assignment | 01-week1-Introduction to deep learning

该系列仅在原课程基础上部分知识点添加个人学习笔记，或相关推导补充等。如有错误，还请批评指教。在学习了 Andrew Ng 课程的基础上，为了更方便的查阅复习，将其整理成文字。因本人一直在学习英语，所以该系列以英文为主，同时也建议读者以英文为主，中文辅助，以便后期进阶时，为学习相关领域的学术论文做铺垫。- ZJ

Coursera 课程 |deeplearning.ai |网易云课堂

---

转载请注明作者和出处：ZJ 微信公众号-「SelfImprovementLab」

知乎：https://zhuanlan.zhihu.com/c_147249273

CSDN：http://blog.csdn.net/JUNJUN_ZHAO/article/details/78875071

---

Introduction to deep learning

Quiz, 10 questions

1. What does the analogy（比喻、类比） “AI is the new electricity” refer to?

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

   • Similar to electricity starting about 100 years ago, AI is transforming multiple industries.正在改变很多个行业
     ( Correct Yes. AI is transforming many fields from the car industry to agriculture to supply-chain…)汽车产业 文化 供应链

   • Through the “smart grid”, AI is delivering a new wave of electricity.

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

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

   • We have access to a lot more data.足够多的数据
     (Correct Yes! The digitalization of our society has played a huge role in this.)

   • Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.深度学习已经在重要的应用领域取得了显著的进步，例如在线广告、语音识别和图像识别。
     (Correct These were all examples discussed in lecture 3.)

   • We have access to a lot more computational power.计算能力的提高
     (Correct Yes! The development of hardware, perhaps especially GPU computing, has significantly improved deep learning algorithms’ performance.)
     硬件的发展，尤其是GPU计算，已经大大改善了深度学习算法的性能。

   • Neural Networks are a brand new field.

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

• Being able to try out ideas quickly allows deep learning engineers to iterate more quickly.
  (Correct ) 能够快速的尝试想法可以让深度学习的工程师更快地迭代。

• Faster computation can help speed up how long a team takes to iterate to a good idea.
  (Correct ) 更快的计算可以帮助加快一个团队迭代一个好主意的时间。

• It is faster to train on a big dataset than a small dataset.
• Recent progress in deep learning algorithms has allowed us to train good models faster (even without changing the CPU/GPU hardware).
  最近在深度学习算法方面的进步使我们能够更快地训练好模型(即使不改变cpu/gpu硬件)。
  (Correct Yes. For example, we discussed how switching from sigmoid to ReLU activation functions allows faster training.)

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?

• True
• False
  (Correct Yes. Finding the characteristics of a model is key to have good performance. Although experience can help, it requires multiple iterations to build a good model.)

5.Which one of these plots represents a ReLU activation function?
- Figure 1:

• Figure 2:

• Figure 3:

（Correct This is the ReLU activation function, the most used in neural networks.）

• Figure 4:

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

• True
• False
  (Correct Yes. Images for cat recognition is an example of “unstructured” data.)

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?

• True
• False
  （Correct A demographic dataset with statistics on different cities’ population, GDP per capita, economic growth is an example of “structured” data by opposition to image, audio or text datasets.
  一个人口统计数据，统计不同城市的人口，人均GDP，经济增长是一个“结构化”数据的例子，它与图像、音频或文本数据集相反。）

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

• It can be trained as a supervised learning problem. 监督学习
  （Correct Yes. We can train it on many pairs of sentences x (English) and y (French).）

• It is strictly more powerful than a Convolutional Neural Network (CNN).

• It is applicable when the input/output is a sequence (e.g., a sequence of words).
  （Correct Yes. An RNN can map from a sequence of english words to a sequence of french words.）

• 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?

• • x-axis is the amount of data
  • y-axis (vertical axis) is the performance of the algorithm.
    （Correct ）
• • x-axis is the input to the algorithm
  • y-axis is outputs.
• • x-axis is the amount of data
  • y-axis is the size of the model you train.
• • x-axis is the performance of the algorithm
  • y-axis (vertical axis) is the amount of data.

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.)

• Increasing the training set size generally does not hurt an algorithm’s performance, and it may help significantly.
  （Correct Yes. Bringing more data to a model is almost always beneficial.）

• Decreasing the training set size generally does not hurt an algorithm’s performance, and it may help significantly.

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

• Increasing the size of a neural network generally does not hurt an algorithm’s performance, and it may help significantly.
  (Correct Yes. According to the trends in the figure above, big networks usually perform better than small networks.)

---

PS: 欢迎扫码关注公众号：「SelfImprovementLab」！专注「深度学习」，「机器学习」，「人工智能」。以及 「早起」，「阅读」，「运动」，「英语 」「其他」不定期建群 打卡互助活动。