Season 5 #Spaic Machine learning Weekly Quiz

Let's say, you are working with categorical feature(s) and you have not looked at the distribution of the categorical variable in the test data. You want to apply one hot encoding (OHE) on the categorical feature(s). What are the challenges you may face?

• Frequency distribution of categories is different in train as compared to the test dataset.

• Train and Test always have same distribution.

• Other challenges

What are support vectors?

• Output vectors that are Closest to the hyperplane

• Output vectors that are farthest from the hyperplane

• Input vectors that are farthest from the hyperplane

• Input vectors that are closest to the hyperplane

Select the application of decision trees in machine learning

• Unsupervised learning

• Infinite attributes

• Flattening nodes

• Classification

What are association rules?

• Correlations and reliability between variables in a dataset

• Correlations and relationships between variables in a dataset

• Assumptions and mentorships between variables in a dataset

• Aggregations and relationships between variables in a dataset

In convolutional neural networks, what does pooling reduce?

• The number of parameters in a network

• How few activations to implement

• The number of max pixels

• Insertions between convolutional layers

What is a Signal?

• An overly complex model

• A random noise in the data

• Data gathering

• The target patterns that you want to learn

Which one of these isn't an indicator of a models quality?

• Consistency

• Feature engineering

• Size of a dataset

• Precision and recall

What is computed by MSE in machine learning?

• Classification

• Entropy

• Bias

• Error

What is feature bagging?

• A random subset of features for each subtree

• Everything you want it to be

• Nothing you want it to be

• A deterministic subset of features for each subtree

What represent the values that will flow through the graph, in computational graph under Tensorflow?

• Tuple

• ops

• Session

• None of these