Practical aspects of Deep Learning

程式碼見博主 Github

1

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

60% train . 20% dev . 20% test

98% train . 1% dev . 1% test
正確

33% train . 33% dev . 33% test

2

The dev and test set should:

Come from the same distribution
正確

Come from different distributions

Be identical to each other (same (x,y) pairs)

Have the same number of examples

3

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

Get more test data
未選擇的是正確的

Add regularization
正確

Make the Neural Network deeper
未選擇的是正確的

Get more training data
正確

Increase the number of units in each hidden layer
未選擇的是正確的

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
正確

Decrease the regularization parameter lambda
未選擇的是正確的

Get more training data
正確

Use a bigger neural network
未選擇的是正確的

5

What is weight decay?

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

A technique to avoid vanishing gradient by imposing a ceiling on the values of the weights.

Gradual corruption of the weights in the neural network if it is trained on noisy data.

The process of gradually decreasing the learning rate during training.

6

What happens when you increase the regularization hyperparameter lambda?

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

Weights are pushed toward becoming bigger (further from 0)

Doubling lambda should roughly result in doubling the weights

Gradient descent taking bigger steps with each iteration (proportional to lambda)

7

ith the inverted dropout technique, at test time:

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

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

正確

You apply dropout (randomly eliminating units) but keep the 1/keep_prob factor in the calculations used in training.

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)

Increasing the regularization effect
未選擇的是正確的

Reducing the regularization effect
正確

Causing the neural network to end up with a higher training set error
未選擇的是正確的

Causing the neural network to end up with a lower training set error
正確

9

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

Data augmentation
正確

Exploding gradient
未選擇的是正確的

L2 regularization
正確

Gradient Checking
未選擇的是正確的

Xavier initialization
未選擇的是正確的

Dropout
正確

Vanishing gradient
未選擇的是正確的

10

Why do we normalize the inputs x?

It makes the parameter initialization faster

It makes it easier to visualize the data

It makes the cost function faster to optimize
正確

Normalization is another word for regularization–It helps to reduce variance