Coursera Machine Learning 第六周 quiz Advice for Applying Machine Learning

1
point

1. 

You train a learning algorithm, and find that it has unacceptably high error on the test set. You plot the learning curve, and obtain the figure below. Is the algorithm suffering from high bias, high variance, or neither?

答案C

Neither

High bias

High variance

1
point

2. 

Suppose you have implemented regularized logistic regression

to classify what object is in an image (i.e., to do object

recognition). However, when you test your hypothesis on a new

set of images, you find that it makes unacceptably large

errors with its predictions on the new images. However, your

hypothesis performs well (has low error) on the

training set. Which of the following are promising steps to

take? Check all that apply.

答案AB

Try using a smaller set of features.

Get more training examples.

Use fewer training examples.

Try adding polynomial features.

1
point

3. 

Suppose you have implemented regularized logistic regression

to predict what items customers will purchase on a web

shopping site. However, when you test your hypothesis on a new

set of customers, you find that it makes unacceptably large

errors in its predictions. Furthermore, the hypothesis

performs poorly on the training set. Which of the

following might be promising steps to take? Check all that

apply.

答案AC

Try adding polynomial features.

Try evaluating the hypothesis on a cross validation set rather than the test set.

Try decreasing the regularization parameter  λ .

Use fewer training examples.

1
point

4. 

Which of the following statements are true? Check all that apply.

答案CD

Suppose you are training a regularized linear regression model. The recommended way to choose what value of regularization parameter  λ  to use is to choose the value of  λ  which gives the lowest test set error.

Suppose you are training a regularized linear regression model.The recommended way to choose what value of regularization parameter  λ  to use is to choose the value of  λ  which gives the lowest training set error.

The performance of a learning algorithm on the training set will typically be better than its performance on the test set.

Suppose you are training a regularized linear regression model. The recommended way to choose what value of regularization parameter  λ  to use is to choose the value of  λ  which gives the lowest cross validation error.

1
point

5. 

Which of the following statements are true? Check all that apply.

答案BCD

We always prefer models with high variance (over those with high bias) as they will able to better fit the training set.

If a learning algorithm is suffering from high bias, only adding more training examples may not improve the test error significantly.

When debugging learning algorithms, it is useful to plot a learning curve to understand if there is a high bias or high variance problem.

If a learning algorithm is suffering from high variance, adding more training examples is likely to improve the test error.