the nuts and bolts of machine learning coursera week 4 quiz answers
Test your knowledge: Additional supervised learning techniques
1. Tree-based learning is a type of unsupervised machine learning that performs classification and regression tasks.
- True
- False
2. Fill in the blank: Similar to a flow chart, a _____ is a classification model that represents various solutions available to solve a given problem based on the possible outcomes of each solution.
- decision tree
- Poisson distribution
- linear regression
- binary logistic regression
3. In a decision tree, which node is the location where the first decision is made?
- Leaf
- Branch
- Root
- Decision
4. In tree-based learning, how is a split determined?
- By the amount of leaves present
- By which variables and cut-off values offer the most predictive power
- By the level of balance present among the predictions made by the model
- By the number of decisions required before arriving at a final prediction
Test your knowledge: Tune tree-based models
5. Fill in the blank: The hyperparameter max depth is used to limit the depth of a decision tree, which is the number of levels between the _____ and the farthest node away from it.
- decision node
- root node
- leaf node
- first split
6. What tuning technique can a data professional use to confirm that a model achieves its intended purpose?
- Classifier
- Min samples leaf
- Grid search
- Decision tree
7. During model validation, the validation dataset must be combined with test data in order to function properly.
- True
- False
8. Fill in the blank: Cross validation involves splitting training data into different combinations of _____, on which the model is trained.
- banks
- parcels
- tiers
- folds
Test your knowledge: Bagging
9. Ensemble learning is most effective when the outputs are aggregated from models that follow the exact same methodology all using the same dataset.
- True
- False
10. What are some of the benefits of ensemble learning? Select all that apply.
- The predictions have lower variance than other standalone models.
- It requires few base learners trained on the same dataset.
- The predictions have less bias than other standalone models.
- It combines the results of many models to help make more reliable predictions.
11. In a random forest, what type of data is used to train the ensemble of decision-tree base learners?
- Duplicated
- Unstructured
- Bootstrapped
- Sampled
12. Fill in the blank: When using a decision tree model, a data professional can use _____ to control the threshold below which nodes become leaves.
- min_samples_leaf
- max_features
- max_depth
- min_samples_split
Test your knowledge: Boosting
13. Fill in the blank: The supervised learning technique boosting builds an ensemble of weak learners _____, then aggregates their predictions.
- in parallel
- repeatedly
- randomly
- sequentially
14. When using a gradient boosting machine (GBM) modeling technique, which term describes a model’s ability to predict new values that fall outside of the range of values in the training data?
- Learning rate
- Cross validation
- Grid search
- Extrapolation
15. When using the hyperparameter min_child_weight, a tree will not split a node if it results in any child node with less weight than what is specified. What happens to the node instead?
- It becomes a root.
- It becomes a leaf
- It gets deleted.
- It duplicates itself to become another node.
Weekly challenge 4
16. Fill in the blank: In tree-based learning, a decision tree’s _____ represent observations about an item.
- roots
- splits
- leaves
- branches
17. Which of the following statements accurately describe decision trees? Select all that apply.
- Decision trees represent solutions to solve a given problem based on possible outcomes of related choices.
- Decision trees are susceptible to overfitting.
- Decision trees are equally effective at predicting both existing and new data.
- Decision trees require no assumptions regarding the distribution of underlying data.
18. Which section of a decision tree is where the final prediction is made?
- Decision node
- Root node
- Leaf node
- Split
19. In a decision tree model, which hyperparameter specifies the number of attributes that each tree selects randomly from the training data to determine its splits?
- Max depth
- Learning rate
- Number of estimators
- Max features
20. What process uses different portions of the data to test and train a model across several iterations?
- Grid search
- Cross validation
- Model validation
- Proportional verification
21. Which of the following statements correctly describe ensemble learning? Select all that apply.
- If a base learner’s prediction is equally effective as a random guess, it is a strong learner.
- A best practice of ensemble learning is to use very different methodologies for each contributing model.
- Ensemble learning involves building multiple models.
- It is possible to use the same methodology for each contributing model, as long as there are numerous base learners.
22. Fill in the blank: Each base learner in a random forest model has different combinations of features available to it, which helps prevent correlated errors among _____ in the ensemble.
- splits
- learners
- roots
- nodes
23. What are some benefits of boosting? Select all that apply.
- The models used in boosting can be trained in parallel across many different servers.
- Boosting does not require the data to be normalized.
- Boosting is robust to outliers.
- Boosting functions well even with multicollinearity among the features.
24. Fill in the blank: In tree-based learning, the decision tree’s _____ represent an item’s target value.
- leaves
- roots
- splits
- branches
25. What are some disadvantages of decision trees? Select all that apply.
- When new data is introduced, decision trees can be less effective at prediction.
- Preparing data to train a decision is a complex process involving significant preprocessing
- Decision trees require assumptions regarding the distribution of underlying data.
- Decision trees can be particularly susceptible to overfitting.
26. In a decision tree model, which hyperparameter sets the threshold below which nodes become leaves?
- Min samples split
- Min samples leaf
- Min samples tree
- Min child weight
27. What practice uses a validation dataset to verify that models are performing as expected?
- Model validation
- Grid search
- Tree verification
- Cross validation
28. Which of the following statements correctly describe ensemble learning? Select all that apply.
- When building an ensemble using different types of models, each should be trained on different data.
- Predictions using an ensemble of models are accurate, even when the individual models are barely more accurate than a random guess.
- Ensemble learning involves aggregating the outputs of multiple models to make a final prediction.
- If a base learner’s prediction is only slightly better than a random guess, it becomes a weak learner.
29. What is the only section of a decision tree that contains no predecessors?
- Split based on what will provide the most predictive power.
- Leaf node
- Root node
- Decision node
30. What practice uses a validation dataset to verify that models are performing as expected?
- Model validation
- Tree verification
- Cross validation
- Grid search
31. Fill in the blank: A random forest model grows trees by taking a random subset of the available features in the training data, then _____ each node at the best feature available to that tree.
- bagging
- tuning
- bootstrapping
- splitting
32. Which of the following statements correctly describe gradient boosting? Select all that apply.
- Each base learner in the sequence is built to predict the residual errors of the model that preceded it.
- Gradient boosting machines have difficulty with extrapolation.
- Gradient boosting models can be trained in parallel.
- Gradient boosting machines can be difficult to interpret.
33. Fill in the blank: In tree-based learning, the decision tree’s _____ represent where the first decision is made.
- roots
- branches
- leaves
- splits
34. Fill in the blank: A random forest is an ensemble of decision-tree _____ that are trained on bootstrapped data.
- observations
- variables
- statements
- base learners
35. What are some benefits of boosting? Select all that apply.
- Boosting scales well to very large datasets.
- Boosting can handle both numeric and categorical features.
- Boosting algorithms are easy to understand.
- Boosting does not require the data to be scaled.
36. Which of the following statements correctly describe gradient boosting? Select all that apply.
- Gradient boosting machines cannot handle messy data.
- Gradient boosting machines do not have coefficients or directionality.
- Gradient boosting machines are often called black-box models because their predictions cannot be explained easily.
- Gradient boosting machines have a lot of hyperparameters.