wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Decision Tree / ensemble methods review

Total questions: 11

Worksheet time: 10mins

Name
Class
Date
1.

What is a Decision Tree?

a)

Flow-Chart

b)

Structure in which internal node represents test on an attribute, each branch represents outcome of test and each leaf node represents class label

c)

Flow-Chart & Structure in which internal node represents test on a feature, each branch represents outcome of test and each leaf node represents class label

d)

None of the mentioned

2.

Decision Trees can be used for regression Tasks

a)

True

b)

False

3.

Decision tree usually underfit the data

a)

True

b)

False

4.

Decision trees are example of model with high variance.

a)

True

b)

False

5.

in a decision tree, If the number of levels is too low i.e. the depth of the tree is too low, the model tends to overfit.

a)

True

b)

False

6.

decision tree is computationally cheap for predictions but training the tree can be computationally expensive

a)

True

b)

False

7.

Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model

a)

True

b)

False

8.

"bagging" ensemble method focuses on decreasing the bais

a)

True

b)

False

9.

Ensemble methods can be divided into two groups, sequential ensemble methods & parallel ensemble methods.


for the sequential ensemble methods, the base learners (estimators) are generated sequentially (e.g. AdaBoost).

a)

True

b)

False

10.

In random forests, each tree in the ensemble is built from a different sample drawn with replacement (i.e. a bootstrap sample) from the training set

a)

True

b)

False

c)

Don't know the answer but i like the meme

d)

Don't know the answer & i'm not a meme person (really?)

11.

in random forest The number of features that will be randomly selected at each split point must be specified as a parameter to the algorithm. we call it max_features.


For regression problem a good default is:

a)

sqrt(p) : where "p" is the total number of features in the training set (rounded down)

b)

p/3 : where "p" is the total number of features in the training set (rounded down)