【中英】【吴恩达课后测验】Course 2 - 改善深层神经网络 - 第一周测验
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。
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% 。
- 【
开发和测试集应该：
- 【
★】来自同一分布。
- 【
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.
- 【
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.
- 【
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。
- 【
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）
- 【
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
- 【
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。
- 【
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
- 【
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
If you have 10,000,000 examples, how would you split the train/dev/test set?
- 98% train . 1% dev . 1% test
The dev and test set should:
- Come from the same distribution
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.
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.
What is weight decay?
- A regularization technique (such as L2 regularization) that results in gradient descent shrinking the weights on every iteration.
What happens when you increase the regularization hyperparameter lambda?
- Weights are pushed toward becoming smaller (closer to 0)
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
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
Which of these techniques are useful for reducing variance (reducing overfitting)? (Check all that apply.)
- Dropout
- L2 regularization
- Data augmentation
Why do we normalize the inputs x?
- It makes the cost function faster to optimize