【中英】【吴恩达课后测验】Course 2 - 改善深层神经网络 - 第一周测验

【中英】【吴恩达课后测验】Course 2 - 改善深层神经网络 - 第一周测验

---

上一篇： 【课程1 - 第四周编程作业】※※※※※ 【回到目录】※※※※※下一篇： 【课程2 - 第一周编程作业】

---

第一周测验 - 深度学习的实践

博主注：以下全部都是只显示正确答案。

1. 如果你有10,000,000个例子，你会如何划分训练/开发/测试集？

   • 【★】训练集占98% ， 开发集占1% ， 测试集占1% 。

2. 开发和测试集应该：

   • 【★】来自同一分布。

3. 如果你的神经网络模型似乎有很高的方差，下列哪个尝试是可能解决问题的？

   • 【★】添加正则化
   • 【★】获取更多的训练数据

   请注意： Check here.

4. 你在一家超市的自动结帐亭工作，正在为苹果，香蕉和橘子制作分类器。 假设您的分类器在训练集上有0.5％的错误，以及开发集上有7％的错误。 以下哪项尝试是有希望改善你的分类器的分类效果的？

   • 【★】增加正则化参数lambda
   • 【★】获取更多的训练数据

   请注意: Check here.

5. 什么是权重衰减？

   • 【★】正则化技术（例如L2正则化）导致梯度下降在每次迭代时权重收缩。

6. 当你增加正则化超参数lambda时会发生什么？

   • 【★】权重会变得更小（接近0）

7. 在测试时候使用dropout：

   • 【★】不要随机消除节点，也不要在训练中使用的计算中保留1 / keep_prob因子

8. 将参数keep_prob从（比如说）0.5增加到0.6可能会导致以下情况

   • 【★】正则化效应被减弱。
   • 【★】使神经网络在结束时会在训练集上表现好一些。

9. 以下哪些技术可用于减少方差（减少过拟合）：

   • 【★】Dropout
   • 【★】L2 正则化
   • 【★】扩充数据集

10. 为什么我们要归一化输入x？

    • 【★】它使成本函数更快地进行优化

---

Week 1 Quiz - Practical aspects of deep learning

1. If you have 10,000,000 examples, how would you split the train/dev/test set?

   • 98% train . 1% dev . 1% test

2. The dev and test set should:

   • Come from the same distribution

3. If your Neural Network model seems to have high variance, what of the following would be promising things to try?

   • Add regularization
   • Get more training data

   Note: Check here.

4. You are working on an automated check-out kiosk for a supermarket, and are building a classifier for apples, bananas and oranges. Suppose your classifier obtains a training set error of 0.5%, and a dev set error of 7%. Which of the following are promising things to try to improve your classifier? (Check all that apply.)

   • Increase the regularization parameter lambda
   • Get more training data

   Note: Check here.

5. What is weight decay?

   • A regularization technique (such as L2 regularization) that results in gradient descent shrinking the weights on every iteration.

6. What happens when you increase the regularization hyperparameter lambda?

   • Weights are pushed toward becoming smaller (closer to 0)

7. With the inverted dropout technique, at test time:

   • You do not apply dropout (do not randomly eliminate units) and do not keep the 1/keep_prob factor in the calculations used in training

8. Increasing the parameter keep_prob from (say) 0.5 to 0.6 will likely cause the following: (Check the two that apply)

   • Reducing the regularization effect
   • Causing the neural network to end up with a lower training set error

9. Which of these techniques are useful for reducing variance (reducing overfitting)? (Check all that apply.)

   • Dropout
   • L2 regularization
   • Data augmentation

10. Why do we normalize the inputs x?

    • It makes the cost function faster to optimize