Supervised and unsupervised learning

A value that defines the step taken at each iteration, before correction?

• Gradient descent

• learning rate

• l2 regularization

• l1 regularization

Adding a new feature to the model always results in equal or better performance on the training set?

• False

• True

Which of the statement about gradient descent is true?

• We find local maxima in gradient descent

• It is an optimization algorithm

The following descriptions best describe what: 1. Value that has to be assigned manually. 2. The K value in K-nearest-neighbor is an example of this. 3. Value is set before the training.

• Centroid

• Model Parameter

• Model hyper parameter

• Significance

Which of these isn’t a classification type?

• Binary classification

• Multiclass multilabel

• Singleclass multilabel

• Multiclass Single Label

Which of these is not a supervised learning algorithm?

• Representation Learning

• Classification

• Regression

Which of these metrics are used to evaluate classification algorithm?

• AUC

• Precision

• Predicted vs True Chart

• F1 Score

Which if these is not a parameter for multi class neural network?

• Regularization Weight

• Number of Hidden Nodes

• Learning Rate

• Number of Learning Iterations

Which of these can be evaluated by a confusion matrix ?

• Recall

• F1 Score

• Precision

• All

Select the odd one out.

• AUC

• ROC

• Logistic Regression